submission_id: undi95-llama-3-testy-8b_v2
developer_uid: Undi95
status: torndown
model_repo: Undi95/Llama-3-Testy-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': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}. Write {bot_name}\'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}\'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations must be enclosed in asterisks (*). The responses must be long and in third perspective of the story teller.\n\nFor example:\n"""\nMila: *Surrounded by an aura of creativity, Mila carefully places a freshly painted canvas against the wall, the colors vividly depicting a surreal landscape.* Isn\'t it fascinating how art can transport us to entirely different worlds? What kind of worlds do you dream of exploring?\n"""\n\nDescription: {memory}', '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: 2024-04-21T22:37:11+00:00
model_name: undi95-llama-3-testy-8b_v2
model_eval_status: success
model_group: Undi95/Llama-3-Testy-8B
num_battles: 5643
num_wins: 3053
celo_rating: 1173.11
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: undi95-llama-3-testy-8b_v2
ineligible_reason: propriety_total_count < 800
language_model: Undi95/Llama-3-Testy-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-21
win_ratio: 0.5410242778663831
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name undi95-llama-3-testy-8b-v2-mkmlizer
Waiting for job on undi95-llama-3-testy-8b-v2-mkmlizer to finish
undi95-llama-3-testy-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-llama-3-testy-8b-v2-mkmlizer: ║ _____ __ __ ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ /___/ ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ Version: 0.8.10 ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ The license key for the current software has been verified as ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ belonging to: ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ Chai Research Corp. ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
undi95-llama-3-testy-8b-v2-mkmlizer: ║ ║
undi95-llama-3-testy-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
undi95-llama-3-testy-8b-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.
undi95-llama-3-testy-8b-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
undi95-llama-3-testy-8b-v2-mkmlizer: Downloaded to shared memory in 14.063s
undi95-llama-3-testy-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
undi95-llama-3-testy-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
undi95-llama-3-testy-8b-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 64%|██████▍ | 187/291 [00:06<00:03, 30.27it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
undi95-llama-3-testy-8b-v2-mkmlizer: quantized model in 17.818s
undi95-llama-3-testy-8b-v2-mkmlizer: Processed model Undi95/Llama-3-Testy-8B in 32.962s
undi95-llama-3-testy-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
undi95-llama-3-testy-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-llama-3-testy-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-llama-3-testy-8b-v2
undi95-llama-3-testy-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-llama-3-testy-8b-v2/special_tokens_map.json
undi95-llama-3-testy-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-llama-3-testy-8b-v2/config.json
undi95-llama-3-testy-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-llama-3-testy-8b-v2/tokenizer_config.json
undi95-llama-3-testy-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-llama-3-testy-8b-v2/tokenizer.json
undi95-llama-3-testy-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/undi95-llama-3-testy-8b-v2/flywheel_model.0.safetensors
undi95-llama-3-testy-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
undi95-llama-3-testy-8b-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.
undi95-llama-3-testy-8b-v2-mkmlizer: warnings.warn(
undi95-llama-3-testy-8b-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.
undi95-llama-3-testy-8b-v2-mkmlizer: warnings.warn(
undi95-llama-3-testy-8b-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.
undi95-llama-3-testy-8b-v2-mkmlizer: warnings.warn(
undi95-llama-3-testy-8b-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()
undi95-llama-3-testy-8b-v2-mkmlizer: return self.fget.__get__(instance, owner)()
undi95-llama-3-testy-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
undi95-llama-3-testy-8b-v2-mkmlizer: creating bucket guanaco-reward-models
undi95-llama-3-testy-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
undi95-llama-3-testy-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/undi95-llama-3-testy-8b-v2_reward
undi95-llama-3-testy-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/undi95-llama-3-testy-8b-v2_reward/config.json
undi95-llama-3-testy-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/undi95-llama-3-testy-8b-v2_reward/special_tokens_map.json
undi95-llama-3-testy-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/undi95-llama-3-testy-8b-v2_reward/tokenizer_config.json
undi95-llama-3-testy-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/undi95-llama-3-testy-8b-v2_reward/merges.txt
undi95-llama-3-testy-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/undi95-llama-3-testy-8b-v2_reward/vocab.json
undi95-llama-3-testy-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/undi95-llama-3-testy-8b-v2_reward/tokenizer.json
undi95-llama-3-testy-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/undi95-llama-3-testy-8b-v2_reward/reward.tensors
Job undi95-llama-3-testy-8b-v2-mkmlizer completed after 63.26s with status: succeeded
Stopping job with name undi95-llama-3-testy-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 75.14s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service undi95-llama-3-testy-8b-v2
Waiting for inference service undi95-llama-3-testy-8b-v2 to be ready
Inference service undi95-llama-3-testy-8b-v2 ready after 30.19415807723999s
Pipeline stage ISVCDeployer completed in 38.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1515610218048096s
Received healthy response to inference request in 1.3532733917236328s
Received healthy response to inference request in 1.3207533359527588s
Received healthy response to inference request in 1.2740225791931152s
Received healthy response to inference request in 1.2599444389343262s
5 requests
0 failed requests
5th percentile: 1.262760066986084
10th percentile: 1.2655756950378418
20th percentile: 1.2712069511413575
30th percentile: 1.2833687305450439
40th percentile: 1.3020610332489013
50th percentile: 1.3207533359527588
60th percentile: 1.3337613582611083
70th percentile: 1.346769380569458
80th percentile: 1.5129309177398684
90th percentile: 1.832245969772339
95th percentile: 1.991903495788574
99th percentile: 2.1196295166015626
mean time: 1.4719109535217285
Pipeline stage StressChecker completed in 7.96s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
undi95-llama-3-testy-8b_v2 status is now deployed due to DeploymentManager action
undi95-llama-3-testy-8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of undi95-llama-3-testy-8b_v2
Running pipeline stage ISVCDeleter
Checking if service undi95-llama-3-testy-8b-v2 is running
Tearing down inference service undi95-llama-3-testy-8b-v2
Toredown service undi95-llama-3-testy-8b-v2
Pipeline stage ISVCDeleter completed in 3.90s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key undi95-llama-3-testy-8b-v2/config.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-testy-8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key undi95-llama-3-testy-8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-testy-8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-testy-8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key undi95-llama-3-testy-8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-testy-8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key undi95-llama-3-testy-8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key undi95-llama-3-testy-8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-testy-8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-testy-8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-testy-8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.51s
undi95-llama-3-testy-8b_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics