submission_id: hastagaras-halu-8b-llama_1139_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Halu-8B-Llama3-Test4-UE
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 100, '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': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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: 2024-05-25T00:45:18+00:00
model_name: test4
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
num_battles: 11129
num_wins: 5914
celo_rating: 1197.58
safety_score: 0.95
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: test4
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Halu-8B-Llama3-Test4-UE
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-24
win_ratio: 0.5314044388534459
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-1139-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-1139-v1-mkmlizer to finish
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama-1139-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-1139-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.
hastagaras-halu-8b-llama-1139-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-1139-v1-mkmlizer: Downloaded to shared memory in 32.567s
hastagaras-halu-8b-llama-1139-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-1139-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-1139-v1-mkmlizer: quantized model in 22.317s
hastagaras-halu-8b-llama-1139-v1-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-Test4-UE in 57.336s
hastagaras-halu-8b-llama-1139-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-1139-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-1139-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-1139-v1
hastagaras-halu-8b-llama-1139-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-1139-v1/config.json
hastagaras-halu-8b-llama-1139-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-1139-v1/special_tokens_map.json
hastagaras-halu-8b-llama-1139-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-1139-v1/tokenizer_config.json
hastagaras-halu-8b-llama-1139-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-1139-v1/tokenizer.json
hastagaras-halu-8b-llama-1139-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-1139-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-1139-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-1139-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.
hastagaras-halu-8b-llama-1139-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-1139-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.
hastagaras-halu-8b-llama-1139-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-1139-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.
hastagaras-halu-8b-llama-1139-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-1139-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()
hastagaras-halu-8b-llama-1139-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-1139-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-1139-v1-mkmlizer: Saving duration: 0.389s
hastagaras-halu-8b-llama-1139-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.171s
hastagaras-halu-8b-llama-1139-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-1139-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-1139-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-1139-v1_reward
hastagaras-halu-8b-llama-1139-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-1139-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama-1139-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-1139-v1_reward/config.json
hastagaras-halu-8b-llama-1139-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-1139-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama-1139-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-1139-v1_reward/vocab.json
hastagaras-halu-8b-llama-1139-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-1139-v1_reward/merges.txt
hastagaras-halu-8b-llama-1139-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-1139-v1_reward/tokenizer.json
hastagaras-halu-8b-llama-1139-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-1139-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama-1139-v1-mkmlizer completed after 93.28s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-1139-v1-mkmlizer
Pipeline stage MKMLizer completed in 97.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-1139-v1
Waiting for inference service hastagaras-halu-8b-llama-1139-v1 to be ready
Inference service hastagaras-halu-8b-llama-1139-v1 ready after 40.23111939430237s
Pipeline stage ISVCDeployer completed in 47.98s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.236734390258789s
Received healthy response to inference request in 1.3450438976287842s
Received healthy response to inference request in 1.3103337287902832s
Received healthy response to inference request in 1.3149440288543701s
Received healthy response to inference request in 1.268594741821289s
5 requests
0 failed requests
5th percentile: 1.276942539215088
10th percentile: 1.2852903366088868
20th percentile: 1.3019859313964843
30th percentile: 1.3112557888031007
40th percentile: 1.3130999088287354
50th percentile: 1.3149440288543701
60th percentile: 1.3269839763641358
70th percentile: 1.3390239238739015
80th percentile: 1.5233819961547854
90th percentile: 1.8800581932067872
95th percentile: 2.058396291732788
99th percentile: 2.201066770553589
mean time: 1.4951301574707032
Pipeline stage StressChecker completed in 8.06s
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-halu-8b-llama_1139_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llama_1139_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics