submission_id: undi95-llama-3-unholy-8b_v1
developer_uid: Undi95
status: torndown
model_repo: Undi95/Llama-3-Unholy-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nThis is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nEngage in a chat with {user_name} while staying in character. Try to flirt with {user_name}. Engage in *roleplay* actions. Describe the scene dramatically.', '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", 'prompt_template': '{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-20T12:20:54+00:00
model_name: undi95-llama-3-unholy-8b_v1
model_eval_status: success
model_group: Undi95/Llama-3-Unholy-8B
num_battles: 5744
num_wins: 2895
celo_rating: 1152.81
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: undi95-llama-3-unholy-8b_v1
ineligible_reason: propriety_total_count < 800
language_model: Undi95/Llama-3-Unholy-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-20
win_ratio: 0.5040041782729805
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name undi95-llama-3-unholy-8b-v1-mkmlizer
Waiting for job on undi95-llama-3-unholy-8b-v1-mkmlizer to finish
undi95-llama-3-unholy-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ _____ __ __ ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ /___/ ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ Version: 0.8.10 ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ belonging to: ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ Chai Research Corp. ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ║ ║
undi95-llama-3-unholy-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
undi95-llama-3-unholy-8b-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.
undi95-llama-3-unholy-8b-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
undi95-llama-3-unholy-8b-v1-mkmlizer: Downloaded to shared memory in 30.092s
undi95-llama-3-unholy-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
undi95-llama-3-unholy-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
undi95-llama-3-unholy-8b-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 80.45it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 85.98it/s] Loading 0: 99%|█████████▊| 287/291 [00:09<00:00, 24.55it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
undi95-llama-3-unholy-8b-v1-mkmlizer: quantized model in 22.721s
undi95-llama-3-unholy-8b-v1-mkmlizer: Processed model Undi95/Llama-3-Unholy-8B in 54.290s
undi95-llama-3-unholy-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
undi95-llama-3-unholy-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-llama-3-unholy-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-llama-3-unholy-8b-v1
undi95-llama-3-unholy-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-llama-3-unholy-8b-v1/config.json
undi95-llama-3-unholy-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-llama-3-unholy-8b-v1/tokenizer_config.json
undi95-llama-3-unholy-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-llama-3-unholy-8b-v1/special_tokens_map.json
undi95-llama-3-unholy-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-llama-3-unholy-8b-v1/tokenizer.json
undi95-llama-3-unholy-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/undi95-llama-3-unholy-8b-v1/flywheel_model.0.safetensors
undi95-llama-3-unholy-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
undi95-llama-3-unholy-8b-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.
undi95-llama-3-unholy-8b-v1-mkmlizer: warnings.warn(
undi95-llama-3-unholy-8b-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.
undi95-llama-3-unholy-8b-v1-mkmlizer: warnings.warn(
undi95-llama-3-unholy-8b-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()
undi95-llama-3-unholy-8b-v1-mkmlizer: return self.fget.__get__(instance, owner)()
undi95-llama-3-unholy-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
undi95-llama-3-unholy-8b-v1-mkmlizer: Saving duration: 0.272s
undi95-llama-3-unholy-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.288s
undi95-llama-3-unholy-8b-v1-mkmlizer: creating bucket guanaco-reward-models
undi95-llama-3-unholy-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
undi95-llama-3-unholy-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v1_reward
undi95-llama-3-unholy-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v1_reward/config.json
undi95-llama-3-unholy-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v1_reward/special_tokens_map.json
undi95-llama-3-unholy-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v1_reward/tokenizer_config.json
undi95-llama-3-unholy-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v1_reward/merges.txt
undi95-llama-3-unholy-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v1_reward/vocab.json
undi95-llama-3-unholy-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v1_reward/tokenizer.json
undi95-llama-3-unholy-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v1_reward/reward.tensors
Job undi95-llama-3-unholy-8b-v1-mkmlizer completed after 73.96s with status: succeeded
Stopping job with name undi95-llama-3-unholy-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service undi95-llama-3-unholy-8b-v1
Waiting for inference service undi95-llama-3-unholy-8b-v1 to be ready
Inference service undi95-llama-3-unholy-8b-v1 ready after 40.2457218170166s
Pipeline stage ISVCDeployer completed in 47.46s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1115870475769043s
Received healthy response to inference request in 1.1983728408813477s
Received healthy response to inference request in 1.1873691082000732s
Received healthy response to inference request in 1.202150821685791s
Received healthy response to inference request in 1.1783356666564941s
5 requests
0 failed requests
5th percentile: 1.18014235496521
10th percentile: 1.1819490432739257
20th percentile: 1.1855624198913575
30th percentile: 1.189569854736328
40th percentile: 1.1939713478088378
50th percentile: 1.1983728408813477
60th percentile: 1.199884033203125
70th percentile: 1.2013952255249023
80th percentile: 1.3840380668640138
90th percentile: 1.747812557220459
95th percentile: 1.9296998023986816
99th percentile: 2.0752095985412597
mean time: 1.375563097000122
Pipeline stage StressChecker completed in 7.55s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.08s
undi95-llama-3-unholy-8b_v1 status is now deployed due to DeploymentManager action
undi95-llama-3-unholy-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of undi95-llama-3-unholy-8b_v1
Running pipeline stage ISVCDeleter
Checking if service undi95-llama-3-unholy-8b-v1 is running
Tearing down inference service undi95-llama-3-unholy-8b-v1
Toredown service undi95-llama-3-unholy-8b-v1
Pipeline stage ISVCDeleter completed in 3.79s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key undi95-llama-3-unholy-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-unholy-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key undi95-llama-3-unholy-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-unholy-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-unholy-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key undi95-llama-3-unholy-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-unholy-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key undi95-llama-3-unholy-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key undi95-llama-3-unholy-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-unholy-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-unholy-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-unholy-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.24s
undi95-llama-3-unholy-8b_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics