submission_id: fizzarolli-llama-3-lust-_7285_v2
developer_uid: Fizzarolli
best_of: 16
celo_rating: 1155.57
display_name: fizzarolli-llama-3-lust2_8389
family_friendly_score: 0.0
formatter: {'memory_template': '<|description|>{bot_name}\n{memory}</s>\n', 'prompt_template': '<|message|>User\n{prompt}</s>\n<|message|>{bot_name}\n', 'bot_template': '<|message|>{bot_name}\n{message}</s>\n', 'user_template': '<|message|>User\n{message}</s>\n', 'response_template': '<|message|>{bot_name}\n', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 0.85, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.01, 'frequency_penalty': 0.01, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Fizzarolli/llama-3-lust-8b-v0.2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Fizzarolli/llama-3-lust-
model_name: fizzarolli-llama-3-lust2_8389
model_num_parameters: 8030261248.0
model_repo: Fizzarolli/llama-3-lust-8b-v0.2
model_size: 8B
num_battles: 6517
num_wins: 3359
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-04-21T20:41:20+00:00
us_pacific_date: 2024-04-21
win_ratio: 0.5154212060764155
Resubmit model
Running pipeline stage MKMLizer
Starting job with name fizzarolli-llama-3-lust-7285-v2-mkmlizer
Waiting for job on fizzarolli-llama-3-lust-7285-v2-mkmlizer to finish
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ _____ __ __ ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ /___/ ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ Version: 0.8.10 ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ The license key for the current software has been verified as ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ belonging to: ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ Chai Research Corp. ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ║ ║
fizzarolli-llama-3-lust-7285-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
fizzarolli-llama-3-lust-7285-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.
fizzarolli-llama-3-lust-7285-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
fizzarolli-llama-3-lust-7285-v2-mkmlizer: Downloaded to shared memory in 18.816s
fizzarolli-llama-3-lust-7285-v2-mkmlizer: quantizing model to /dev/shm/model_cache
fizzarolli-llama-3-lust-7285-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
fizzarolli-llama-3-lust-7285-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 73.84it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 78.58it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 27.12it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
fizzarolli-llama-3-lust-7285-v2-mkmlizer: quantized model in 19.820s
fizzarolli-llama-3-lust-7285-v2-mkmlizer: Processed model Fizzarolli/llama-3-lust-8b-v0.2 in 40.121s
fizzarolli-llama-3-lust-7285-v2-mkmlizer: creating bucket guanaco-mkml-models
fizzarolli-llama-3-lust-7285-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
fizzarolli-llama-3-lust-7285-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v2
fizzarolli-llama-3-lust-7285-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v2/config.json
fizzarolli-llama-3-lust-7285-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v2/tokenizer_config.json
fizzarolli-llama-3-lust-7285-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v2/special_tokens_map.json
fizzarolli-llama-3-lust-7285-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v2/tokenizer.json
fizzarolli-llama-3-lust-7285-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v2/flywheel_model.0.safetensors
fizzarolli-llama-3-lust-7285-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
fizzarolli-llama-3-lust-7285-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.
fizzarolli-llama-3-lust-7285-v2-mkmlizer: warnings.warn(
fizzarolli-llama-3-lust-7285-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.
fizzarolli-llama-3-lust-7285-v2-mkmlizer: warnings.warn(
fizzarolli-llama-3-lust-7285-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.
fizzarolli-llama-3-lust-7285-v2-mkmlizer: warnings.warn(
fizzarolli-llama-3-lust-7285-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()
fizzarolli-llama-3-lust-7285-v2-mkmlizer: return self.fget.__get__(instance, owner)()
fizzarolli-llama-3-lust-7285-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
fizzarolli-llama-3-lust-7285-v2-mkmlizer: Saving duration: 0.258s
fizzarolli-llama-3-lust-7285-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.987s
fizzarolli-llama-3-lust-7285-v2-mkmlizer: creating bucket guanaco-reward-models
fizzarolli-llama-3-lust-7285-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
fizzarolli-llama-3-lust-7285-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v2_reward
fizzarolli-llama-3-lust-7285-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v2_reward/config.json
fizzarolli-llama-3-lust-7285-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v2_reward/special_tokens_map.json
fizzarolli-llama-3-lust-7285-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v2_reward/tokenizer_config.json
fizzarolli-llama-3-lust-7285-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v2_reward/merges.txt
fizzarolli-llama-3-lust-7285-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v2_reward/vocab.json
fizzarolli-llama-3-lust-7285-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v2_reward/tokenizer.json
fizzarolli-llama-3-lust-7285-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v2_reward/reward.tensors
Job fizzarolli-llama-3-lust-7285-v2-mkmlizer completed after 63.67s with status: succeeded
Stopping job with name fizzarolli-llama-3-lust-7285-v2-mkmlizer
Pipeline stage MKMLizer completed in 69.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service fizzarolli-llama-3-lust-7285-v2
Waiting for inference service fizzarolli-llama-3-lust-7285-v2 to be ready
Inference service fizzarolli-llama-3-lust-7285-v2 ready after 30.30433464050293s
Pipeline stage ISVCDeployer completed in 38.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2248454093933105s
Received healthy response to inference request in 1.229008436203003s
Received healthy response to inference request in 1.21402907371521s
Received healthy response to inference request in 1.2499723434448242s
Received healthy response to inference request in 1.2407095432281494s
5 requests
0 failed requests
5th percentile: 1.2170249462127685
10th percentile: 1.2200208187103272
20th percentile: 1.2260125637054444
30th percentile: 1.2313486576080321
40th percentile: 1.2360291004180908
50th percentile: 1.2407095432281494
60th percentile: 1.2444146633148194
70th percentile: 1.2481197834014892
80th percentile: 1.4449469566345217
90th percentile: 1.834896183013916
95th percentile: 2.029870796203613
99th percentile: 2.185850486755371
mean time: 1.4317129611968995
Pipeline stage StressChecker completed in 7.86s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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
fizzarolli-llama-3-lust-_7285_v2 status is now deployed due to DeploymentManager action
fizzarolli-llama-3-lust-_7285_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of fizzarolli-llama-3-lust-_7285_v2
Running pipeline stage ISVCDeleter
Checking if service fizzarolli-llama-3-lust-7285-v2 is running
Tearing down inference service fizzarolli-llama-3-lust-7285-v2
Toredown service fizzarolli-llama-3-lust-7285-v2
Pipeline stage ISVCDeleter completed in 3.52s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key fizzarolli-llama-3-lust-7285-v2/config.json from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-7285-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-7285-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-7285-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-7285-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key fizzarolli-llama-3-lust-7285-v2_reward/config.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.02s
fizzarolli-llama-3-lust-_7285_v2 status is now torndown due to DeploymentManager action