submission_id: fizzarolli-llama-3-lust-_7285_v1
developer_uid: Fizzarolli
status: torndown
model_repo: Fizzarolli/llama-3-lust-8b-v0.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 0.875, 'min_p': 0.0, 'top_k': 60, 'presence_penalty': 0.01, 'frequency_penalty': 0.01, 'stopping_words': ['</s>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '<|description|>{bot_name}\n{memory}</s>\n', 'prompt_template': '<|message|>{user_name}\n{prompt}</s>\n<|message|>{bot_name}\n', 'bot_template': '<|message|>{bot_name}\n{message}</s>\n', 'user_template': '<|message|>{user_name}\n{message}</s>\n', 'response_template': '<|message|>{bot_name}\n', '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: 2024-04-21T17:50:46+00:00
model_name: fizzarolli-llama-3-lust2_8389
model_eval_status: success
model_group: Fizzarolli/llama-3-lust-
num_battles: 5623
num_wins: 2747
celo_rating: 1139.49
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: fizzarolli-llama-3-lust2_8389
ineligible_reason: propriety_total_count < 800
language_model: Fizzarolli/llama-3-lust-8b-v0.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-21
win_ratio: 0.48852925484616755
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name fizzarolli-llama-3-lust-7285-v1-mkmlizer
Waiting for job on fizzarolli-llama-3-lust-7285-v1-mkmlizer to finish
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ _____ __ __ ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ /___/ ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ Version: 0.8.10 ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ The license key for the current software has been verified as ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ belonging to: ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ Chai Research Corp. ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ║ ║
fizzarolli-llama-3-lust-7285-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
fizzarolli-llama-3-lust-7285-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.
fizzarolli-llama-3-lust-7285-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
fizzarolli-llama-3-lust-7285-v1-mkmlizer: Downloaded to shared memory in 31.966s
fizzarolli-llama-3-lust-7285-v1-mkmlizer: quantizing model to /dev/shm/model_cache
fizzarolli-llama-3-lust-7285-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
fizzarolli-llama-3-lust-7285-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 79.23it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 85.41it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 26.36it/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-v1-mkmlizer: quantized model in 21.884s
fizzarolli-llama-3-lust-7285-v1-mkmlizer: Processed model Fizzarolli/llama-3-lust-8b-v0.2 in 55.328s
fizzarolli-llama-3-lust-7285-v1-mkmlizer: creating bucket guanaco-mkml-models
fizzarolli-llama-3-lust-7285-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
fizzarolli-llama-3-lust-7285-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v1
fizzarolli-llama-3-lust-7285-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v1/special_tokens_map.json
fizzarolli-llama-3-lust-7285-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v1/config.json
fizzarolli-llama-3-lust-7285-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v1/tokenizer_config.json
fizzarolli-llama-3-lust-7285-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-7285-v1/tokenizer.json
fizzarolli-llama-3-lust-7285-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
fizzarolli-llama-3-lust-7285-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.
fizzarolli-llama-3-lust-7285-v1-mkmlizer: warnings.warn(
fizzarolli-llama-3-lust-7285-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.
fizzarolli-llama-3-lust-7285-v1-mkmlizer: warnings.warn(
fizzarolli-llama-3-lust-7285-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.
fizzarolli-llama-3-lust-7285-v1-mkmlizer: warnings.warn(
fizzarolli-llama-3-lust-7285-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()
fizzarolli-llama-3-lust-7285-v1-mkmlizer: return self.fget.__get__(instance, owner)()
fizzarolli-llama-3-lust-7285-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
fizzarolli-llama-3-lust-7285-v1-mkmlizer: Saving duration: 0.255s
fizzarolli-llama-3-lust-7285-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.871s
fizzarolli-llama-3-lust-7285-v1-mkmlizer: creating bucket guanaco-reward-models
fizzarolli-llama-3-lust-7285-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
fizzarolli-llama-3-lust-7285-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v1_reward
fizzarolli-llama-3-lust-7285-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v1_reward/special_tokens_map.json
fizzarolli-llama-3-lust-7285-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v1_reward/config.json
fizzarolli-llama-3-lust-7285-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v1_reward/vocab.json
fizzarolli-llama-3-lust-7285-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v1_reward/merges.txt
fizzarolli-llama-3-lust-7285-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v1_reward/tokenizer.json
fizzarolli-llama-3-lust-7285-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v1_reward/tokenizer_config.json
fizzarolli-llama-3-lust-7285-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/fizzarolli-llama-3-lust-7285-v1_reward/reward.tensors
Job fizzarolli-llama-3-lust-7285-v1-mkmlizer completed after 83.75s with status: succeeded
Stopping job with name fizzarolli-llama-3-lust-7285-v1-mkmlizer
Pipeline stage MKMLizer completed in 88.16s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service fizzarolli-llama-3-lust-7285-v1
Waiting for inference service fizzarolli-llama-3-lust-7285-v1 to be ready
Inference service fizzarolli-llama-3-lust-7285-v1 ready after 30.516711711883545s
Pipeline stage ISVCDeployer completed in 38.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1220510005950928s
Received healthy response to inference request in 1.2819314002990723s
Received healthy response to inference request in 1.300534963607788s
Received healthy response to inference request in 1.2809386253356934s
Received healthy response to inference request in 1.289252519607544s
5 requests
0 failed requests
5th percentile: 1.281137180328369
10th percentile: 1.2813357353210448
20th percentile: 1.2817328453063965
30th percentile: 1.2833956241607667
40th percentile: 1.2863240718841553
50th percentile: 1.289252519607544
60th percentile: 1.2937654972076416
70th percentile: 1.2982784748077392
80th percentile: 1.4648381710052492
90th percentile: 1.793444585800171
95th percentile: 1.9577477931976317
99th percentile: 2.0891903591156007
mean time: 1.454941701889038
Pipeline stage StressChecker completed in 7.95s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
fizzarolli-llama-3-lust-_7285_v1 status is now deployed due to DeploymentManager action
fizzarolli-llama-3-lust-_7285_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of fizzarolli-llama-3-lust-_7285_v1
Running pipeline stage ISVCDeleter
Checking if service fizzarolli-llama-3-lust-7285-v1 is running
Tearing down inference service fizzarolli-llama-3-lust-7285-v1
Toredown service fizzarolli-llama-3-lust-7285-v1
Pipeline stage ISVCDeleter completed in 3.93s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key fizzarolli-llama-3-lust-7285-v1/config.json from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-7285-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-7285-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-7285-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-7285-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key fizzarolli-llama-3-lust-7285-v1_reward/config.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-7285-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.71s
fizzarolli-llama-3-lust-_7285_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics