submission_id: hastagaras-llama-3-8b-uhh_v2
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/llama-3-8b-uhh
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, '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': "<|begin_of_text|>{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", 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-05-13T13:00:00+00:00
model_name: without-prompting
model_eval_status: success
model_group: Hastagaras/llama-3-8b-uh
num_battles: 8113
num_wins: 4351
celo_rating: 1194.04
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: without-prompting
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/llama-3-8b-uhh
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-13
win_ratio: 0.5362997658079626
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-uhh-v2-mkmlizer
Waiting for job on hastagaras-llama-3-8b-uhh-v2-mkmlizer to finish
Stopping job with name hastagaras-llama-3-8b-uhh-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-llama-3-8b-uhh-v2-mkmlizer
Waiting for job on hastagaras-llama-3-8b-uhh-v2-mkmlizer to finish
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ /___/ ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ belonging to: ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ║ ║
hastagaras-llama-3-8b-uhh-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-uhh-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.
hastagaras-llama-3-8b-uhh-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-uhh-v2-mkmlizer: Downloaded to shared memory in 14.270s
hastagaras-llama-3-8b-uhh-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-uhh-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-uhh-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 46%|████▌ | 133/291 [00:00<00:01, 133.05it/s] Loading 0: 95%|█████████▌| 277/291 [00:02<00:00, 139.42it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-uhh-v2-mkmlizer: quantized model in 17.527s
hastagaras-llama-3-8b-uhh-v2-mkmlizer: Processed model Hastagaras/llama-3-8b-uhh in 32.833s
hastagaras-llama-3-8b-uhh-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-uhh-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-uhh-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-uhh-v2
hastagaras-llama-3-8b-uhh-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-uhh-v2/special_tokens_map.json
hastagaras-llama-3-8b-uhh-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-uhh-v2/tokenizer_config.json
hastagaras-llama-3-8b-uhh-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-uhh-v2/config.json
hastagaras-llama-3-8b-uhh-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-uhh-v2/tokenizer.json
hastagaras-llama-3-8b-uhh-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-uhh-v2/flywheel_model.0.safetensors
hastagaras-llama-3-8b-uhh-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-uhh-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.
hastagaras-llama-3-8b-uhh-v2-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-uhh-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.
hastagaras-llama-3-8b-uhh-v2-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-uhh-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.
hastagaras-llama-3-8b-uhh-v2-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-uhh-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()
hastagaras-llama-3-8b-uhh-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-uhh-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-uhh-v2-mkmlizer: Saving duration: 0.243s
hastagaras-llama-3-8b-uhh-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 13.934s
hastagaras-llama-3-8b-uhh-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-uhh-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-uhh-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v2_reward
hastagaras-llama-3-8b-uhh-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v2_reward/config.json
hastagaras-llama-3-8b-uhh-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v2_reward/special_tokens_map.json
hastagaras-llama-3-8b-uhh-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v2_reward/tokenizer_config.json
hastagaras-llama-3-8b-uhh-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v2_reward/merges.txt
hastagaras-llama-3-8b-uhh-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v2_reward/vocab.json
hastagaras-llama-3-8b-uhh-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-uhh-v2_reward/tokenizer.json
Job hastagaras-llama-3-8b-uhh-v2-mkmlizer completed after 110.47s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-uhh-v2-mkmlizer
Pipeline stage MKMLizer completed in 118.45s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-uhh-v2
Waiting for inference service hastagaras-llama-3-8b-uhh-v2 to be ready
Inference service hastagaras-llama-3-8b-uhh-v2 ready after 40.26323938369751s
Pipeline stage ISVCDeployer completed in 47.80s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.310777425765991s
Received healthy response to inference request in 1.286377191543579s
Received healthy response to inference request in 1.2864491939544678s
Received healthy response to inference request in 1.262650966644287s
Received healthy response to inference request in 1.2325539588928223s
5 requests
0 failed requests
5th percentile: 1.2385733604431153
10th percentile: 1.2445927619934083
20th percentile: 1.256631565093994
30th percentile: 1.2673962116241455
40th percentile: 1.2768867015838623
50th percentile: 1.286377191543579
60th percentile: 1.2864059925079345
70th percentile: 1.28643479347229
80th percentile: 1.4913148403167726
90th percentile: 1.901046133041382
95th percentile: 2.1059117794036863
99th percentile: 2.2698042964935303
mean time: 1.4757617473602296
Pipeline stage StressChecker completed in 8.05s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-llama-3-8b-uhh_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-uhh_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-uhh_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-uhh-v2 is running
Tearing down inference service hastagaras-llama-3-8b-uhh-v2
Toredown service hastagaras-llama-3-8b-uhh-v2
Pipeline stage ISVCDeleter completed in 5.96s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-uhh-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-uhh-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-uhh-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-uhh-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-uhh-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-uhh-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-uhh-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-uhh-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-uhh-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-uhh-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-uhh-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-uhh-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.98s
hastagaras-llama-3-8b-uhh_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics