submission_id: vicgalle-roleplay-llama-3-8b_v16
developer_uid: chai_backend_admin
status: torndown
model_repo: vicgalle/Roleplay-Llama-3-8B
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'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-24T09:01:46+00:00
model_name: vicgalle-roleplay-llama-3-8b_v16
model_eval_status: success
model_group: vicgalle/Roleplay-Llama-
num_battles: 7706
num_wins: 3783
celo_rating: 1143.61
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 3000000000.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: vicgalle-roleplay-llama-3-8b_v16
ineligible_reason: propriety_total_count < 800
language_model: vicgalle/Roleplay-Llama-3-8B
model_size: 3B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-24
win_ratio: 0.49091616921879055
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name vicgalle-roleplay-llama-3-8b-v16-mkmlizer
Waiting for job on vicgalle-roleplay-llama-3-8b-v16-mkmlizer to finish
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ _____ __ __ ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ /___/ ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ Version: 0.8.10 ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ The license key for the current software has been verified as ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ belonging to: ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ Chai Research Corp. ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ║ ║
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
vicgalle-roleplay-llama-3-8b-v16-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-v16-mkmlizer: warnings.warn(warning_message, FutureWarning)
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: Downloaded to shared memory in 27.197s
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: quantizing model to /dev/shm/model_cache
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:01, 101.96it/s] Loading 0: 71%|███████ | 206/291 [00:02<00:00, 102.97it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 30.34it/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-v16-mkmlizer: quantized model in 18.326s
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: Processed model vicgalle/Roleplay-Llama-3-8B in 46.483s
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: creating bucket guanaco-mkml-models
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v16
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v16/tokenizer_config.json
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v16/special_tokens_map.json
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v16/config.json
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v16/tokenizer.json
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/vicgalle-roleplay-llama-3-8b-v16/flywheel_model.0.safetensors
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
vicgalle-roleplay-llama-3-8b-v16-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.
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: warnings.warn(
vicgalle-roleplay-llama-3-8b-v16-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-v16-mkmlizer: warnings.warn(
vicgalle-roleplay-llama-3-8b-v16-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-v16-mkmlizer: warnings.warn(
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: creating bucket guanaco-reward-models
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: Bucket 's3://guanaco-reward-models/' created
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v16_reward
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v16_reward/vocab.json
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v16_reward/tokenizer_config.json
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v16_reward/config.json
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v16_reward/special_tokens_map.json
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v16_reward/merges.txt
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v16_reward/tokenizer.json
vicgalle-roleplay-llama-3-8b-v16-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/vicgalle-roleplay-llama-3-8b-v16_reward/reward.tensors
Job vicgalle-roleplay-llama-3-8b-v16-mkmlizer completed after 73.76s with status: succeeded
Stopping job with name vicgalle-roleplay-llama-3-8b-v16-mkmlizer
Pipeline stage MKMLizer completed in 74.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.26s
Running pipeline stage ISVCDeployer
Creating inference service vicgalle-roleplay-llama-3-8b-v16
Waiting for inference service vicgalle-roleplay-llama-3-8b-v16 to be ready
Inference service vicgalle-roleplay-llama-3-8b-v16 ready after 40.62381887435913s
Pipeline stage ISVCDeployer completed in 46.89s
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.2119271755218506s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.4288511276245117s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.3888089656829834s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.3197569847106934s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.3282272815704346s
5 requests
0 failed requests
5th percentile: 1.3214510440826417
10th percentile: 1.3231451034545898
20th percentile: 1.3265332221984862
30th percentile: 1.3403436183929442
40th percentile: 1.3645762920379638
50th percentile: 1.3888089656829834
60th percentile: 1.4048258304595946
70th percentile: 1.420842695236206
80th percentile: 1.5854663372039797
90th percentile: 1.8986967563629151
95th percentile: 2.0553119659423826
99th percentile: 2.180604133605957
mean time: 1.5355143070220947
Pipeline stage StressChecker completed in 9.99s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.09s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.09s
Running M-Eval for topic stay_in_character
vicgalle-roleplay-llama-3-8b_v16 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
%s, retrying in %s seconds...
vicgalle-roleplay-llama-3-8b_v16 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of vicgalle-roleplay-llama-3-8b_v16
Running pipeline stage ISVCDeleter
Checking if service vicgalle-roleplay-llama-3-8b-v16 is running
Tearing down inference service vicgalle-roleplay-llama-3-8b-v16
Toredown service vicgalle-roleplay-llama-3-8b-v16
Pipeline stage ISVCDeleter completed in 3.88s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v16/config.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v16/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v16/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v16/tokenizer.json from bucket guanaco-mkml-models
Deleting key vicgalle-roleplay-llama-3-8b-v16/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key vicgalle-roleplay-llama-3-8b-v16_reward/config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v16_reward/merges.txt from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v16_reward/reward.tensors from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v16_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v16_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v16_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key vicgalle-roleplay-llama-3-8b-v16_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.83s
vicgalle-roleplay-llama-3-8b_v16 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics