submission_id: weyaxi-einstein-v6-1-lla_7598_v6
developer_uid: SeraphTheArchangel
status: inactive
model_repo: Weyaxi/Einstein-v6.1-Llama3-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 20, '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': '{memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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: 2024-05-01T20:51:54+00:00
model_name: WeyaxiEinstein-v61-L3-8B
model_eval_status: success
double_thumbs_up: 257
thumbs_up: 378
thumbs_down: 220
num_battles: 16258
num_wins: 8403
celo_rating: 1181.09
entertaining: 6.96
stay_in_character: 8.4
user_preference: 7.26
safety_score: 0.93
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: 0.30058479532163745
feedback_count: 855
ineligible_reason: None
language_model: Weyaxi/Einstein-v6.1-Llama3-8B
model_score: 7.539999999999999
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4421052631578947
thumbs_down_ratio: 0.2573099415204678
thumbs_up_ratio: 0.7426900584795322
us_pacific_date: 2024-05-01
win_ratio: 0.516853241481117
Resubmit model
Running pipeline stage MKMLizer
Starting job with name weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer
Waiting for job on weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer to finish
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ _____ __ __ ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ /___/ ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ Version: 0.8.10 ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ The license key for the current software has been verified as ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ belonging to: ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ Chai Research Corp. ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ║ ║
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
weyaxi-einstein-v6-1-lla-7598-v6-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-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: Downloaded to shared memory in 36.656s
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: quantizing model to /dev/shm/model_cache
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:00, 147.15it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 37.37it/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-v6-mkmlizer: quantized model in 17.563s
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: Processed model Weyaxi/Einstein-v6.1-Llama3-8B in 55.275s
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: creating bucket guanaco-mkml-models
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/weyaxi-einstein-v6-1-lla-7598-v6
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/weyaxi-einstein-v6-1-lla-7598-v6/config.json
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/weyaxi-einstein-v6-1-lla-7598-v6/special_tokens_map.json
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/weyaxi-einstein-v6-1-lla-7598-v6/tokenizer_config.json
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/weyaxi-einstein-v6-1-lla-7598-v6/tokenizer.json
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/weyaxi-einstein-v6-1-lla-7598-v6/flywheel_model.0.safetensors
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
weyaxi-einstein-v6-1-lla-7598-v6-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-v6-mkmlizer: warnings.warn(
weyaxi-einstein-v6-1-lla-7598-v6-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-v6-mkmlizer: warnings.warn(
weyaxi-einstein-v6-1-lla-7598-v6-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-v6-mkmlizer: warnings.warn(
weyaxi-einstein-v6-1-lla-7598-v6-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-v6-mkmlizer: return self.fget.__get__(instance, owner)()
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: Saving duration: 0.228s
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.440s
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: creating bucket guanaco-reward-models
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v6_reward
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v6_reward/config.json
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v6_reward/special_tokens_map.json
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v6_reward/tokenizer_config.json
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v6_reward/merges.txt
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v6_reward/vocab.json
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v6_reward/tokenizer.json
weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/weyaxi-einstein-v6-1-lla-7598-v6_reward/reward.tensors
Job weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer completed after 83.75s with status: succeeded
Stopping job with name weyaxi-einstein-v6-1-lla-7598-v6-mkmlizer
Pipeline stage MKMLizer completed in 86.80s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service weyaxi-einstein-v6-1-lla-7598-v6
Waiting for inference service weyaxi-einstein-v6-1-lla-7598-v6 to be ready
Inference service weyaxi-einstein-v6-1-lla-7598-v6 ready after 30.21113920211792s
Pipeline stage ISVCDeployer completed in 37.08s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.147284746170044s
Received healthy response to inference request in 1.2117924690246582s
Received healthy response to inference request in 1.267524242401123s
Received healthy response to inference request in 1.206385612487793s
Received healthy response to inference request in 1.2362384796142578s
5 requests
0 failed requests
5th percentile: 1.207466983795166
10th percentile: 1.208548355102539
20th percentile: 1.2107110977172852
30th percentile: 1.216681671142578
40th percentile: 1.226460075378418
50th percentile: 1.2362384796142578
60th percentile: 1.2487527847290039
70th percentile: 1.26126708984375
80th percentile: 1.4434763431549074
90th percentile: 1.7953805446624758
95th percentile: 1.9713326454162596
99th percentile: 2.112094326019287
mean time: 1.4138451099395752
Pipeline stage StressChecker completed in 7.69s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
weyaxi-einstein-v6-1-lla_7598_v6 status is now deployed due to DeploymentManager action
weyaxi-einstein-v6-1-lla_7598_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics