submission_id: cgato-l3-thespice-8b-v0-6-3_v5
developer_uid: c.gato
status: torndown
model_repo: cgato/L3-TheSpice-8b-v0.6.3
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': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n {bot_name} responds in one line. {bot_name} gives casual responses.\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'User: {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: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-21T12:19:31+00:00
model_name: cgato-l3-thespice-8b-v0-6-3_v5
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-v0.
num_battles: 6476
num_wins: 3561
celo_rating: 1184.38
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: cgato-l3-thespice-8b-v0-6-3_v5
ineligible_reason: propriety_total_count < 800
language_model: cgato/L3-TheSpice-8b-v0.6.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-21
win_ratio: 0.5498764669549104
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer to finish
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-v0-6-3-v5-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.
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: Downloaded to shared memory in 11.469s
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 129.58it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 127.75it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 29.32it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: quantized model in 17.746s
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: Processed model cgato/L3-TheSpice-8b-v0.6.3 in 30.369s
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-6-3-v5
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-6-3-v5/special_tokens_map.json
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-6-3-v5/config.json
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-6-3-v5/tokenizer_config.json
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-6-3-v5/tokenizer.json
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-6-3-v5/flywheel_model.0.safetensors
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-v0-6-3-v5-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.
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-6-3-v5-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.
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-6-3-v5-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.
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-6-3-v5-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()
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: Saving duration: 0.245s
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.463s
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-6-3-v5_reward
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-6-3-v5_reward/config.json
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-6-3-v5_reward/special_tokens_map.json
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-6-3-v5_reward/tokenizer_config.json
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-6-3-v5_reward/merges.txt
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-6-3-v5_reward/vocab.json
cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-6-3-v5_reward/tokenizer.json
Job cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer completed after 66.99s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-v0-6-3-v5-mkmlizer
Pipeline stage MKMLizer completed in 72.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-v0-6-3-v5
Waiting for inference service cgato-l3-thespice-8b-v0-6-3-v5 to be ready
Inference service cgato-l3-thespice-8b-v0-6-3-v5 ready after 40.32831382751465s
Pipeline stage ISVCDeployer completed in 47.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.109684944152832s
Received healthy response to inference request in 1.272519826889038s
Received healthy response to inference request in 1.2509934902191162s
Received healthy response to inference request in 1.2768824100494385s
Received healthy response to inference request in 1.268376350402832s
5 requests
0 failed requests
5th percentile: 1.2544700622558593
10th percentile: 1.2579466342926025
20th percentile: 1.264899778366089
30th percentile: 1.2692050457000732
40th percentile: 1.2708624362945558
50th percentile: 1.272519826889038
60th percentile: 1.2742648601531983
70th percentile: 1.2760098934173585
80th percentile: 1.4434429168701173
90th percentile: 1.7765639305114747
95th percentile: 1.9431244373321532
99th percentile: 2.0763728427886963
mean time: 1.4356914043426514
Pipeline stage StressChecker completed in 7.80s
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
cgato-l3-thespice-8b-v0-6-3_v5 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-v0-6-3_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-v0-6-3_v5
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-v0-6-3-v5 is running
Tearing down inference service cgato-l3-thespice-8b-v0-6-3-v5
Toredown service cgato-l3-thespice-8b-v0-6-3-v5
Pipeline stage ISVCDeleter completed in 3.92s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-6-3-v5/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-6-3-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-6-3-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-6-3-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-6-3-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-6-3-v5_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-6-3-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-6-3-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-6-3-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-6-3-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-6-3-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-6-3-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.39s
cgato-l3-thespice-8b-v0-6-3_v5 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics