submission_id: hastagaras-llama3-8b-meh_v1
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/llama3-8b-meh
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|><|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: 2024-05-12T21:36:34+00:00
model_name: hastagaras-llama3-8b-meh_v1
model_eval_status: success
model_group: Hastagaras/llama3-8b-meh
num_battles: 27548
num_wins: 14719
celo_rating: 1192.01
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: 0.5343037607085814
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-8b-meh-v1-mkmlizer
Waiting for job on hastagaras-llama3-8b-meh-v1-mkmlizer to finish
hastagaras-llama3-8b-meh-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ /___/ ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ belonging to: ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ║ ║
hastagaras-llama3-8b-meh-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-meh-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-llama3-8b-meh-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-meh-v1-mkmlizer: Downloaded to shared memory in 29.013s
hastagaras-llama3-8b-meh-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-8b-meh-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-8b-meh-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 127.96it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 127.22it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 29.08it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-8b-meh-v1-mkmlizer: quantized model in 17.779s
hastagaras-llama3-8b-meh-v1-mkmlizer: Processed model Hastagaras/llama3-8b-meh in 47.906s
hastagaras-llama3-8b-meh-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-meh-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-meh-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-meh-v1
hastagaras-llama3-8b-meh-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-meh-v1/config.json
hastagaras-llama3-8b-meh-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-meh-v1/special_tokens_map.json
hastagaras-llama3-8b-meh-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-meh-v1/tokenizer_config.json
hastagaras-llama3-8b-meh-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-meh-v1/tokenizer.json
hastagaras-llama3-8b-meh-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-8b-meh-v1/flywheel_model.0.safetensors
hastagaras-llama3-8b-meh-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-meh-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-llama3-8b-meh-v1-mkmlizer: warnings.warn(
hastagaras-llama3-8b-meh-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-llama3-8b-meh-v1-mkmlizer: warnings.warn(
hastagaras-llama3-8b-meh-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-llama3-8b-meh-v1-mkmlizer: warnings.warn(
hastagaras-llama3-8b-meh-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-llama3-8b-meh-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-meh-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-meh-v1-mkmlizer: Saving duration: 0.246s
hastagaras-llama3-8b-meh-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.398s
hastagaras-llama3-8b-meh-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-8b-meh-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-8b-meh-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-8b-meh-v1_reward
hastagaras-llama3-8b-meh-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-8b-meh-v1_reward/tokenizer_config.json
hastagaras-llama3-8b-meh-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-8b-meh-v1_reward/special_tokens_map.json
hastagaras-llama3-8b-meh-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-8b-meh-v1_reward/merges.txt
hastagaras-llama3-8b-meh-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-8b-meh-v1_reward/config.json
hastagaras-llama3-8b-meh-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-8b-meh-v1_reward/vocab.json
hastagaras-llama3-8b-meh-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-8b-meh-v1_reward/tokenizer.json
hastagaras-llama3-8b-meh-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-meh-v1_reward/reward.tensors
Job hastagaras-llama3-8b-meh-v1-mkmlizer completed after 83.19s with status: succeeded
Stopping job with name hastagaras-llama3-8b-meh-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.71s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-meh-v1
Waiting for inference service hastagaras-llama3-8b-meh-v1 to be ready
Inference service hastagaras-llama3-8b-meh-v1 ready after 40.22430634498596s
Pipeline stage ISVCDeployer completed in 47.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.213118553161621s
Received healthy response to inference request in 1.3512094020843506s
Received healthy response to inference request in 1.2777535915374756s
Received healthy response to inference request in 1.4653785228729248s
Received healthy response to inference request in 1.2781867980957031s
5 requests
0 failed requests
5th percentile: 1.2778402328491212
10th percentile: 1.2779268741607666
20th percentile: 1.2781001567840575
30th percentile: 1.2927913188934326
40th percentile: 1.3220003604888917
50th percentile: 1.3512094020843506
60th percentile: 1.3968770503997803
70th percentile: 1.44254469871521
80th percentile: 1.6149265289306642
90th percentile: 1.9140225410461427
95th percentile: 2.0635705471038817
99th percentile: 2.183208951950073
mean time: 1.517129373550415
Pipeline stage StressChecker completed in 8.19s
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
hastagaras-llama3-8b-meh_v1 status is now deployed due to DeploymentManager action
hastagaras-llama3-8b-meh_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-8b-meh_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-8b-meh-v1 is running
Tearing down inference service hastagaras-llama3-8b-meh-v1
Toredown service hastagaras-llama3-8b-meh-v1
Pipeline stage ISVCDeleter completed in 5.89s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-meh-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-meh-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-meh-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-meh-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-meh-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-meh-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-meh-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.89s
hastagaras-llama3-8b-meh_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics