submission_id: wespro-llama3-rplora-sma_7364_v2
developer_uid: WesPro
status: torndown
model_repo: WesPro/Llama3-RPLoRa-SmaugOrpo
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': 4, 'max_output_tokens': 64}
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}
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: 2024-04-21T13:13:30+00:00
model_name: wespro-llama3-rplora-sma_7364_v2
model_eval_status: success
model_group: WesPro/Llama3-RPLoRa-Sma
num_battles: 6818
num_wins: 3378
celo_rating: 1146.31
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: wespro-llama3-rplora-sma_7364_v2
ineligible_reason: propriety_total_count < 800
language_model: WesPro/Llama3-RPLoRa-SmaugOrpo
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-21
win_ratio: 0.4954532120856556
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name wespro-llama3-rplora-sma-7364-v2-mkmlizer
Waiting for job on wespro-llama3-rplora-sma-7364-v2-mkmlizer to finish
Stopping job with name wespro-llama3-rplora-sma-7364-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name wespro-llama3-rplora-sma-7364-v2-mkmlizer
Waiting for job on wespro-llama3-rplora-sma-7364-v2-mkmlizer to finish
Stopping job with name wespro-llama3-rplora-sma-7364-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name wespro-llama3-rplora-sma-7364-v2-mkmlizer
Waiting for job on wespro-llama3-rplora-sma-7364-v2-mkmlizer to finish
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ _____ __ __ ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ /___/ ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ Version: 0.8.10 ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ The license key for the current software has been verified as ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ belonging to: ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ Chai Research Corp. ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ║ ║
wespro-llama3-rplora-sma-7364-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
wespro-llama3-rplora-sma-7364-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.
wespro-llama3-rplora-sma-7364-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
wespro-llama3-rplora-sma-7364-v2-mkmlizer: Downloaded to shared memory in 15.647s
wespro-llama3-rplora-sma-7364-v2-mkmlizer: quantizing model to /dev/shm/model_cache
wespro-llama3-rplora-sma-7364-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
wespro-llama3-rplora-sma-7364-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 46%|████▌ | 134/291 [00:01<00:01, 132.37it/s] Loading 0: 64%|██████▍ | 187/291 [00:07<00:05, 20.78it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
wespro-llama3-rplora-sma-7364-v2-mkmlizer: quantized model in 19.356s
wespro-llama3-rplora-sma-7364-v2-mkmlizer: Processed model WesPro/Llama3-RPLoRa-SmaugOrpo in 36.480s
wespro-llama3-rplora-sma-7364-v2-mkmlizer: creating bucket guanaco-mkml-models
wespro-llama3-rplora-sma-7364-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
wespro-llama3-rplora-sma-7364-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/wespro-llama3-rplora-sma-7364-v2
wespro-llama3-rplora-sma-7364-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/wespro-llama3-rplora-sma-7364-v2/config.json
wespro-llama3-rplora-sma-7364-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/wespro-llama3-rplora-sma-7364-v2/special_tokens_map.json
wespro-llama3-rplora-sma-7364-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/wespro-llama3-rplora-sma-7364-v2/tokenizer_config.json
wespro-llama3-rplora-sma-7364-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/wespro-llama3-rplora-sma-7364-v2/tokenizer.json
wespro-llama3-rplora-sma-7364-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/wespro-llama3-rplora-sma-7364-v2/flywheel_model.0.safetensors
wespro-llama3-rplora-sma-7364-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
wespro-llama3-rplora-sma-7364-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.
wespro-llama3-rplora-sma-7364-v2-mkmlizer: warnings.warn(
wespro-llama3-rplora-sma-7364-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.
wespro-llama3-rplora-sma-7364-v2-mkmlizer: warnings.warn(
wespro-llama3-rplora-sma-7364-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.
wespro-llama3-rplora-sma-7364-v2-mkmlizer: warnings.warn(
wespro-llama3-rplora-sma-7364-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()
wespro-llama3-rplora-sma-7364-v2-mkmlizer: return self.fget.__get__(instance, owner)()
wespro-llama3-rplora-sma-7364-v2-mkmlizer: creating bucket guanaco-reward-models
wespro-llama3-rplora-sma-7364-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
wespro-llama3-rplora-sma-7364-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/wespro-llama3-rplora-sma-7364-v2_reward
wespro-llama3-rplora-sma-7364-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/wespro-llama3-rplora-sma-7364-v2_reward/special_tokens_map.json
wespro-llama3-rplora-sma-7364-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/wespro-llama3-rplora-sma-7364-v2_reward/tokenizer_config.json
wespro-llama3-rplora-sma-7364-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/wespro-llama3-rplora-sma-7364-v2_reward/config.json
wespro-llama3-rplora-sma-7364-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/wespro-llama3-rplora-sma-7364-v2_reward/merges.txt
wespro-llama3-rplora-sma-7364-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/wespro-llama3-rplora-sma-7364-v2_reward/vocab.json
wespro-llama3-rplora-sma-7364-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/wespro-llama3-rplora-sma-7364-v2_reward/tokenizer.json
wespro-llama3-rplora-sma-7364-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/wespro-llama3-rplora-sma-7364-v2_reward/reward.tensors
Job wespro-llama3-rplora-sma-7364-v2-mkmlizer completed after 66.55s with status: succeeded
Stopping job with name wespro-llama3-rplora-sma-7364-v2-mkmlizer
Pipeline stage MKMLizer completed in 83.94s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service wespro-llama3-rplora-sma-7364-v2
Waiting for inference service wespro-llama3-rplora-sma-7364-v2 to be ready
Tearing down inference service wespro-llama3-rplora-sma-7364-v2
%s, retrying in %s seconds...
Creating inference service wespro-llama3-rplora-sma-7364-v2
Waiting for inference service wespro-llama3-rplora-sma-7364-v2 to be ready
Tearing down inference service wespro-llama3-rplora-sma-7364-v2
%s, retrying in %s seconds...
Creating inference service wespro-llama3-rplora-sma-7364-v2
Waiting for inference service wespro-llama3-rplora-sma-7364-v2 to be ready
Inference service wespro-llama3-rplora-sma-7364-v2 ready after 50.437538623809814s
Pipeline stage ISVCDeployer completed in 92.75s
Running pipeline stage StressChecker
Received healthy response to inference request in 8.175384521484375s
Received healthy response to inference request in 2.1797423362731934s
Received healthy response to inference request in 1.1583831310272217s
Received healthy response to inference request in 1.1352169513702393s
Received healthy response to inference request in 1.2188997268676758s
5 requests
0 failed requests
5th percentile: 1.1398501873016358
10th percentile: 1.1444834232330323
20th percentile: 1.1537498950958252
30th percentile: 1.1704864501953125
40th percentile: 1.1946930885314941
50th percentile: 1.2188997268676758
60th percentile: 1.6032367706298827
70th percentile: 1.9875738143920896
80th percentile: 3.378870773315431
90th percentile: 5.777127647399903
95th percentile: 6.976256084442138
99th percentile: 7.935558834075928
mean time: 2.773525333404541
Pipeline stage StressChecker completed in 14.78s
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 0.10s
wespro-llama3-rplora-sma_7364_v2 status is now deployed due to DeploymentManager action
wespro-llama3-rplora-sma_7364_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of wespro-llama3-rplora-sma_7364_v2
Running pipeline stage ISVCDeleter
Checking if service wespro-llama3-rplora-sma-7364-v2 is running
Tearing down inference service wespro-llama3-rplora-sma-7364-v2
Toredown service wespro-llama3-rplora-sma-7364-v2
Pipeline stage ISVCDeleter completed in 7.93s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key wespro-llama3-rplora-sma-7364-v2/config.json from bucket guanaco-mkml-models
Deleting key wespro-llama3-rplora-sma-7364-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key wespro-llama3-rplora-sma-7364-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key wespro-llama3-rplora-sma-7364-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key wespro-llama3-rplora-sma-7364-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key wespro-llama3-rplora-sma-7364-v2_reward/config.json from bucket guanaco-reward-models
Deleting key wespro-llama3-rplora-sma-7364-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key wespro-llama3-rplora-sma-7364-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key wespro-llama3-rplora-sma-7364-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key wespro-llama3-rplora-sma-7364-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key wespro-llama3-rplora-sma-7364-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key wespro-llama3-rplora-sma-7364-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.95s
wespro-llama3-rplora-sma_7364_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics