submission_id: cycy233-l3-fusion-v0-e3-0_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-fusion-v0-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: 2024-07-01T04:17:05+00:00
model_name: cycy233-l3-fusion-v0-e3-0_v1
model_group: cycy233/L3-fusion-v0-e3.
num_battles: 15135
num_wins: 7574
celo_rating: 1185.5
propriety_score: 0.7016402714932126
propriety_total_count: 7072.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cycy233-l3-fusion-v0-e3-0_v1
ineligible_reason: None
language_model: cycy233/L3-fusion-v0-e3.0
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-30
win_ratio: 0.500429468120251
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-fusion-v0-e3-0-v1-mkmlizer
Waiting for job on cycy233-l3-fusion-v0-e3-0-v1-mkmlizer to finish
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ /___/ ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ║ ║
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-fusion-v0-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-v0-e3-0-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: Downloaded to shared memory in 33.695s
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 78.72it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 93.58it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 135.72it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: quantized model in 23.721s
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: Processed model cycy233/L3-fusion-v0-e3.0 in 60.018s
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-fusion-v0-e3-0-v1
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-fusion-v0-e3-0-v1/config.json
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-fusion-v0-e3-0-v1/special_tokens_map.json
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-fusion-v0-e3-0-v1/tokenizer_config.json
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-fusion-v0-e3-0-v1/tokenizer.json
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-fusion-v0-e3-0-v1/flywheel_model.0.safetensors
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-fusion-v0-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-v0-e3-0-v1-mkmlizer: warnings.warn(
cycy233-l3-fusion-v0-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-v0-e3-0-v1-mkmlizer: warnings.warn(
cycy233-l3-fusion-v0-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-v0-e3-0-v1-mkmlizer: warnings.warn(
cycy233-l3-fusion-v0-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-v0-e3-0-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: Saving duration: 0.410s
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.203s
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-fusion-v0-e3-0-v1_reward
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-fusion-v0-e3-0-v1_reward/config.json
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-fusion-v0-e3-0-v1_reward/tokenizer_config.json
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-fusion-v0-e3-0-v1_reward/special_tokens_map.json
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-fusion-v0-e3-0-v1_reward/merges.txt
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-fusion-v0-e3-0-v1_reward/vocab.json
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-fusion-v0-e3-0-v1_reward/tokenizer.json
cycy233-l3-fusion-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-fusion-v0-e3-0-v1_reward/reward.tensors
Job cycy233-l3-fusion-v0-e3-0-v1-mkmlizer completed after 93.69s with status: succeeded
Stopping job with name cycy233-l3-fusion-v0-e3-0-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-fusion-v0-e3-0-v1
Waiting for inference service cycy233-l3-fusion-v0-e3-0-v1 to be ready
Inference service cycy233-l3-fusion-v0-e3-0-v1 ready after 40.190412282943726s
Pipeline stage ISVCDeployer completed in 46.96s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.211439371109009s
Received healthy response to inference request in 1.371863842010498s
Received healthy response to inference request in 1.3403303623199463s
Received healthy response to inference request in 1.2846086025238037s
Received healthy response to inference request in 1.3612205982208252s
5 requests
0 failed requests
5th percentile: 1.2957529544830322
10th percentile: 1.3068973064422607
20th percentile: 1.3291860103607178
30th percentile: 1.344508409500122
40th percentile: 1.3528645038604736
50th percentile: 1.3612205982208252
60th percentile: 1.3654778957366944
70th percentile: 1.3697351932525634
80th percentile: 1.5397789478302004
90th percentile: 1.8756091594696045
95th percentile: 2.0435242652893066
99th percentile: 2.1778563499450683
mean time: 1.5138925552368163
Pipeline stage StressChecker completed in 8.33s
cycy233-l3-fusion-v0-e3-0_v1 status is now deployed due to DeploymentManager action
cycy233-l3-fusion-v0-e3-0_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics