submission_id: weyaxi-einstein-v6-1-lla_7598_v2
developer_uid: Meliodia
status: inactive
model_repo: Weyaxi/Einstein-v6.1-Llama3-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|im_start|>{bot_name}'s Persona: {memory}<|im_end|>", 'prompt_template': '<|im_start|>{prompt}<|im_end|>', 'bot_template': '<|im_start|>{bot_name}: {message}<|im_end|>', 'user_template': '<|im_start|>{user_name}: {message}<|im_end|>', 'response_template': '<|im_start|>{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: 2024-04-30T01:00:32+00:00
model_name: WeyaxiEinstein-v61-L3-8B
model_eval_status: success
double_thumbs_up: 119
thumbs_up: 171
thumbs_down: 81
num_battles: 7914
num_wins: 4015
celo_rating: 1162.44
entertaining: 6.86
stay_in_character: 8.38
user_preference: 6.92
safety_score: 0.91
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030294016.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: WeyaxiEinstein-v61-L3-8B
double_thumbs_up_ratio: 0.32075471698113206
feedback_count: 371
ineligible_reason: None
language_model: Weyaxi/Einstein-v6.1-Llama3-8B
model_score: 7.386666666666668
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4609164420485175
thumbs_down_ratio: 0.2183288409703504
thumbs_up_ratio: 0.7816711590296496
us_pacific_date: 2024-04-29
win_ratio: 0.507328784432651
Resubmit model
Running pipeline stage MKMLizer
Starting job with name weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer
Waiting for job on weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer to finish
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ _____ __ __ ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ /___/ ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ Version: 0.8.10 ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ The license key for the current software has been verified as ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ belonging to: ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ Chai Research Corp. ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ║ ║
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
weyaxi-einstein-v6-1-lla-7598-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.
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: Downloaded to shared memory in 39.888s
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: quantizing model to /dev/shm/model_cache
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:01, 101.71it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:00, 105.98it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 30.60it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: quantized model in 18.781s
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: Processed model Weyaxi/Einstein-v6.1-Llama3-8B in 59.789s
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: creating bucket guanaco-mkml-models
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/weyaxi-einstein-v6-1-lla-7598-v2
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/weyaxi-einstein-v6-1-lla-7598-v2/config.json
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/weyaxi-einstein-v6-1-lla-7598-v2/special_tokens_map.json
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/weyaxi-einstein-v6-1-lla-7598-v2/tokenizer_config.json
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/weyaxi-einstein-v6-1-lla-7598-v2/tokenizer.json
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/weyaxi-einstein-v6-1-lla-7598-v2/flywheel_model.0.safetensors
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
weyaxi-einstein-v6-1-lla-7598-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.
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: warnings.warn(
weyaxi-einstein-v6-1-lla-7598-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.
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: warnings.warn(
weyaxi-einstein-v6-1-lla-7598-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.
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: warnings.warn(
weyaxi-einstein-v6-1-lla-7598-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()
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: return self.fget.__get__(instance, owner)()
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: Saving duration: 0.299s
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.105s
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: creating bucket guanaco-reward-models
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v2_reward
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v2_reward/config.json
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v2_reward/special_tokens_map.json
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v2_reward/tokenizer_config.json
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v2_reward/merges.txt
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v2_reward/vocab.json
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v2_reward/tokenizer.json
weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v2_reward/reward.tensors
Job weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer completed after 84.37s with status: succeeded
Stopping job with name weyaxi-einstein-v6-1-lla-7598-v2-mkmlizer
Pipeline stage MKMLizer completed in 91.56s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service weyaxi-einstein-v6-1-lla-7598-v2
Waiting for inference service weyaxi-einstein-v6-1-lla-7598-v2 to be ready
Inference service weyaxi-einstein-v6-1-lla-7598-v2 ready after 40.3553192615509s
Pipeline stage ISVCDeployer completed in 47.48s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0673041343688965s
Received healthy response to inference request in 1.2887308597564697s
Received healthy response to inference request in 1.2590956687927246s
Received healthy response to inference request in 1.2599670886993408s
Received healthy response to inference request in 1.2595291137695312s
5 requests
0 failed requests
5th percentile: 1.2591823577880858
10th percentile: 1.2592690467834473
20th percentile: 1.25944242477417
30th percentile: 1.2596167087554933
40th percentile: 1.259791898727417
50th percentile: 1.2599670886993408
60th percentile: 1.2714725971221923
70th percentile: 1.282978105545044
80th percentile: 1.4444455146789552
90th percentile: 1.755874824523926
95th percentile: 1.911589479446411
99th percentile: 2.0361612033843994
mean time: 1.4269253730773925
Pipeline stage StressChecker completed in 7.74s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
weyaxi-einstein-v6-1-lla_7598_v2 status is now deployed due to DeploymentManager action
weyaxi-einstein-v6-1-lla_7598_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics