submission_id: cgato-l3-thespice-8b-v0-1-3_v9
developer_uid: c.gato
best_of: 16
celo_rating: 1180.21
display_name: cgato-l3-thespice-8b-v0-1-3_v9
family_friendly_score: 0.0
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n {bot_name} responds in one line.\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}
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}
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: cgato/L3-TheSpice-8b-v0.1.3
max_input_tokens: 512
max_output_tokens: 112
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-v0.
model_name: cgato-l3-thespice-8b-v0-1-3_v9
model_num_parameters: 8030261248.0
model_repo: cgato/L3-TheSpice-8b-v0.1.3
model_size: 8B
num_battles: 7306
num_wins: 3981
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n {bot_name} gives single line responses.\n{bot_name} gives short responses.\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-04-21T13:02:58+00:00
us_pacific_date: 2024-04-21
win_ratio: 0.5448946071721873
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer to finish
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-v0-1-3-v9-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-v0-1-3-v9-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: Downloaded to shared memory in 13.340s
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▉ | 84/291 [00:01<00:02, 83.78it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 91.84it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 29.20it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: quantized model in 19.909s
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: Processed model cgato/L3-TheSpice-8b-v0.1.3 in 34.382s
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v9
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v9/config.json
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v9/special_tokens_map.json
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v9/tokenizer_config.json
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v9/tokenizer.json
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v9/flywheel_model.0.safetensors
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-v0-1-3-v9-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-v0-1-3-v9-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-1-3-v9-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-v0-1-3-v9-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-1-3-v9-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-v0-1-3-v9-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-1-3-v9-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-v0-1-3-v9-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: Saving duration: 0.263s
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.129s
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v9_reward
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v9_reward/special_tokens_map.json
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v9_reward/config.json
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v9_reward/merges.txt
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v9_reward/vocab.json
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v9_reward/tokenizer_config.json
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v9_reward/tokenizer.json
cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v9_reward/reward.tensors
Job cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer completed after 64.25s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-v0-1-3-v9-mkmlizer
Pipeline stage MKMLizer completed in 69.11s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-v0-1-3-v9
Waiting for inference service cgato-l3-thespice-8b-v0-1-3-v9 to be ready
Inference service cgato-l3-thespice-8b-v0-1-3-v9 ready after 40.700892210006714s
Pipeline stage ISVCDeployer completed in 48.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.785252332687378s
Received healthy response to inference request in 1.972144365310669s
Received healthy response to inference request in 1.982973575592041s
Received healthy response to inference request in 2.1329474449157715s
Received healthy response to inference request in 1.999405860900879s
5 requests
0 failed requests
5th percentile: 1.9743102073669434
10th percentile: 1.9764760494232179
20th percentile: 1.9808077335357666
30th percentile: 1.9862600326538087
40th percentile: 1.9928329467773438
50th percentile: 1.999405860900879
60th percentile: 2.052822494506836
70th percentile: 2.106239128112793
80th percentile: 2.2634084224700928
90th percentile: 2.5243303775787354
95th percentile: 2.6547913551330566
99th percentile: 2.7591601371765138
mean time: 2.1745447158813476
Pipeline stage StressChecker completed in 11.56s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-v0-1-3_v9 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-v0-1-3_v9 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-v0-1-3_v9
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-v0-1-3-v9 is running
Tearing down inference service cgato-l3-thespice-8b-v0-1-3-v9
Toredown service cgato-l3-thespice-8b-v0-1-3-v9
Pipeline stage ISVCDeleter completed in 4.13s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-1-3-v9/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v9/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v9/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v9/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v9/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-1-3-v9_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v9_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v9_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v9_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v9_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v9_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v9_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.76s
cgato-l3-thespice-8b-v0-1-3_v9 status is now torndown due to DeploymentManager action