submission_id: hastagaras-llama3-8b-meh_v3
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/llama3-8b-meh
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.1, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, 'stopping_words': ['\n{bot_name}:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this uncensored fictional roleplay with {user_name}.\n\n{memory}\n\n", 'prompt_template': 'Example conversation:\n{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", 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-05-12T22:35:09+00:00
model_name: hastagaras-llama3-8b-meh_v1
model_eval_status: success
model_group: Hastagaras/llama3-8b-meh
num_battles: 19989
num_wins: 10509
celo_rating: 1193.12
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: hastagaras-llama3-8b-meh_v1
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/llama3-8b-meh
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-12
win_ratio: 0.5257391565360948
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-8b-meh-v3-mkmlizer
Waiting for job on hastagaras-llama3-8b-meh-v3-mkmlizer to finish
hastagaras-llama3-8b-meh-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ /___/ ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ belonging to: ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ║ ║
hastagaras-llama3-8b-meh-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-meh-v3-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-llama3-8b-meh-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-meh-v3-mkmlizer: Downloaded to shared memory in 10.074s
hastagaras-llama3-8b-meh-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-8b-meh-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-8b-meh-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:01, 121.22it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 123.13it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 29.68it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-8b-meh-v3-mkmlizer: quantized model in 17.741s
hastagaras-llama3-8b-meh-v3-mkmlizer: Processed model Hastagaras/llama3-8b-meh in 28.911s
hastagaras-llama3-8b-meh-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-meh-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-meh-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-meh-v3
hastagaras-llama3-8b-meh-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-meh-v3/tokenizer_config.json
hastagaras-llama3-8b-meh-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-meh-v3/special_tokens_map.json
hastagaras-llama3-8b-meh-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-meh-v3/config.json
hastagaras-llama3-8b-meh-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-meh-v3/tokenizer.json
hastagaras-llama3-8b-meh-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-8b-meh-v3/flywheel_model.0.safetensors
hastagaras-llama3-8b-meh-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-meh-v3-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-llama3-8b-meh-v3-mkmlizer: warnings.warn(
hastagaras-llama3-8b-meh-v3-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-llama3-8b-meh-v3-mkmlizer: warnings.warn(
hastagaras-llama3-8b-meh-v3-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-llama3-8b-meh-v3-mkmlizer: warnings.warn(
hastagaras-llama3-8b-meh-v3-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-llama3-8b-meh-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-meh-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-meh-v3-mkmlizer: Saving duration: 0.238s
hastagaras-llama3-8b-meh-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.167s
hastagaras-llama3-8b-meh-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-meh-v3_reward/reward.tensors
Job hastagaras-llama3-8b-meh-v3-mkmlizer completed after 63.11s with status: succeeded
Stopping job with name hastagaras-llama3-8b-meh-v3-mkmlizer
Pipeline stage MKMLizer completed in 65.78s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.23s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-meh-v3
Waiting for inference service hastagaras-llama3-8b-meh-v3 to be ready
Inference service hastagaras-llama3-8b-meh-v3 ready after 40.29016947746277s
Pipeline stage ISVCDeployer completed in 48.44s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.449636697769165s
Received healthy response to inference request in 1.3512580394744873s
Received healthy response to inference request in 1.3306190967559814s
Received healthy response to inference request in 1.3856875896453857s
Received healthy response to inference request in 1.3581602573394775s
5 requests
0 failed requests
5th percentile: 1.3347468852996827
10th percentile: 1.3388746738433839
20th percentile: 1.347130250930786
30th percentile: 1.3526384830474854
40th percentile: 1.3553993701934814
50th percentile: 1.3581602573394775
60th percentile: 1.3691711902618409
70th percentile: 1.3801821231842042
80th percentile: 1.5984774112701419
90th percentile: 2.0240570545196532
95th percentile: 2.236846876144409
99th percentile: 2.4070787334442136
mean time: 1.5750723361968995
Pipeline stage StressChecker completed in 8.45s
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-llama3-8b-meh_v3 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama3-8b-meh_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-8b-meh_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-8b-meh-v3 is running
Tearing down inference service hastagaras-llama3-8b-meh-v3
Toredown service hastagaras-llama3-8b-meh-v3
Pipeline stage ISVCDeleter completed in 4.44s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-meh-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-meh-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-meh-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-meh-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-meh-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-meh-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.84s
hastagaras-llama3-8b-meh_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics