submission_id: vicgalle-roleplay-llama-3-8b_v7
developer_uid: Bytes512
status: torndown
model_repo: vicgalle/Roleplay-Llama-3-8B
reward_repo: rirv938/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'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 112}
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': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-04-21T12:22:59+00:00
model_name: vicgalle-roleplay-llama-3-8b_v2
model_eval_status: success
model_group: vicgalle/Roleplay-Llama-
num_battles: 6175
num_wins: 3631
celo_rating: 1211.12
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: 112
display_name: vicgalle-roleplay-llama-3-8b_v2
ineligible_reason: max_output_tokens!=64
language_model: vicgalle/Roleplay-Llama-3-8B
model_size: 8B
reward_model: rirv938/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-21
win_ratio: 0.5880161943319838
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name vicgalle-roleplay-llama-3-8b-v7-mkmlizer
Waiting for job on vicgalle-roleplay-llama-3-8b-v7-mkmlizer to finish
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ _____ __ __ ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ /___/ ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ Version: 0.8.10 ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ The license key for the current software has been verified as ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ belonging to: ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ Chai Research Corp. ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
vicgalle-roleplay-llama-3-8b-v7-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.
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: warnings.warn(warning_message, FutureWarning)
Scoring model output for bot %s
Failed to get response for submission blend_nadin_2024-03-31: ('http://thanhdaonguyen-once-upon-a-t-v38-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:46020->127.0.0.1:8080: read: connection reset by peer\n')
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: Downloaded to shared memory in 25.238s
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: quantizing model to /dev/shm/model_cache
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Completed M-Eval for topic user_preference, average_score=7.58
Running M-Eval for topic entertaining
M-Eval Dataset for topic entertaining is loaded
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 71.64it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 77.84it/s] Loading 0: 97%|█████████▋| 281/291 [00:03<00:00, 84.37it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: quantized model in 20.721s
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: Processed model vicgalle/Roleplay-Llama-3-8B in 47.433s
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: creating bucket guanaco-mkml-models
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v7
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v7/flywheel_model.0.safetensors
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
vicgalle-roleplay-llama-3-8b-v7-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.
Scoring model output for bot %s
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: warnings.warn(
vicgalle-roleplay-llama-3-8b-v7-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.
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: warnings.warn(
vicgalle-roleplay-llama-3-8b-v7-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.
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: warnings.warn(
vicgalle-roleplay-llama-3-8b-v7-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()
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: return self.fget.__get__(instance, owner)()
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: Saving duration: 0.279s
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.730s
vicgalle-roleplay-llama-3-8b-v7-mkmlizer: creating bucket guanaco-reward-models
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Job vicgalle-roleplay-llama-3-8b-v7-mkmlizer completed after 73.85s with status: succeeded
Stopping job with name vicgalle-roleplay-llama-3-8b-v7-mkmlizer
Pipeline stage MKMLizer completed in 74.21s
Running pipeline stage MKMLKubeTemplater
Received score %s for bot %s
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service vicgalle-roleplay-llama-3-8b-v7
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Waiting for inference service vicgalle-roleplay-llama-3-8b-v7 to be ready
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Completed M-Eval for topic entertaining, average_score=7.08
Inference service vicgalle-roleplay-llama-3-8b-v7 ready after 40.224745750427246s
Pipeline stage ISVCDeployer completed in 45.86s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.726273536682129s
Received healthy response to inference request in 2.11464262008667s
Received healthy response to inference request in 2.1795101165771484s
Received healthy response to inference request in 2.019508123397827s
Received healthy response to inference request in 2.022914409637451s
5 requests
0 failed requests
5th percentile: 2.020189380645752
10th percentile: 2.020870637893677
20th percentile: 2.0222331523895263
30th percentile: 2.0412600517272947
40th percentile: 2.0779513359069823
50th percentile: 2.11464262008667
60th percentile: 2.1405896186828612
70th percentile: 2.1665366172790526
80th percentile: 2.2888628005981446
90th percentile: 2.5075681686401365
95th percentile: 2.6169208526611327
99th percentile: 2.7044029998779298
mean time: 2.212569761276245
Pipeline stage StressChecker completed in 12.14s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.07s
M-Eval Dataset for topic stay_in_character is loaded
vicgalle-roleplay-llama-3-8b_v7 status is now deployed due to DeploymentManager action
vicgalle-roleplay-llama-3-8b_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of vicgalle-roleplay-llama-3-8b_v7
Running pipeline stage ISVCDeleter
Checking if service vicgalle-roleplay-llama-3-8b-v7 is running
Tearing down inference service vicgalle-roleplay-llama-3-8b-v7
Toredown service vicgalle-roleplay-llama-3-8b-v7
Pipeline stage ISVCDeleter completed in 3.79s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v7/config.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v7_reward/config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.35s
vicgalle-roleplay-llama-3-8b_v7 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics