submission_id: cgato-l3-thespice-8b-v0-1-3_v7
developer_uid: c.gato
status: torndown
model_repo: cgato/L3-TheSpice-8b-v0.1.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 70, 'presence_penalty': 0.9, 'frequency_penalty': 0.9, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 112}
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}
reward_formatter: {'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', 'bot_template': '{bot_name}: {message}\n{bot_name}: {message}\n{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-21T12:49:23+00:00
model_name: cgato-l3-thespice-8b-v0-1-3_v7
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-v0.
num_battles: 5455
num_wins: 2619
celo_rating: 1136.53
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: cgato-l3-thespice-8b-v0-1-3_v7
ineligible_reason: max_output_tokens!=64
language_model: cgato/L3-TheSpice-8b-v0.1.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-21
win_ratio: 0.48010999083409717
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer to finish
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-v0-1-3-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.
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: Downloaded to shared memory in 28.361s
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▉ | 84/291 [00:01<00:02, 82.46it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 89.85it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 27.42it/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-v7-mkmlizer: quantized model in 19.630s
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: Processed model cgato/L3-TheSpice-8b-v0.1.3 in 49.450s
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v7
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v7/config.json
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v7/special_tokens_map.json
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v7/tokenizer_config.json
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v7/tokenizer.json
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v7/flywheel_model.0.safetensors
cgato-l3-thespice-8b-v0-1-3-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.
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-1-3-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()
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: Saving duration: 0.266s
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.745s
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v7_reward
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v7_reward/special_tokens_map.json
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v7_reward/tokenizer_config.json
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v7_reward/vocab.json
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v7_reward/merges.txt
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v7_reward/tokenizer.json
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v7_reward/config.json
cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v7_reward/reward.tensors
Job cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer completed after 82.3s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-v0-1-3-v7-mkmlizer
Pipeline stage MKMLizer completed in 86.95s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-v0-1-3-v7
Waiting for inference service cgato-l3-thespice-8b-v0-1-3-v7 to be ready
Inference service cgato-l3-thespice-8b-v0-1-3-v7 ready after 30.20625591278076s
Pipeline stage ISVCDeployer completed in 37.96s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.758543014526367s
Received healthy response to inference request in 2.0188117027282715s
Received healthy response to inference request in 2.0835514068603516s
Received healthy response to inference request in 1.9979188442230225s
Received healthy response to inference request in 2.0103096961975098s
5 requests
0 failed requests
5th percentile: 2.0003970146179197
10th percentile: 2.0028751850128175
20th percentile: 2.0078315258026125
30th percentile: 2.012010097503662
40th percentile: 2.015410900115967
50th percentile: 2.0188117027282715
60th percentile: 2.0447075843811033
70th percentile: 2.0706034660339356
80th percentile: 2.2185497283935547
90th percentile: 2.488546371459961
95th percentile: 2.623544692993164
99th percentile: 2.7315433502197264
mean time: 2.1738269329071045
Pipeline stage StressChecker completed in 11.47s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
cgato-l3-thespice-8b-v0-1-3_v7 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-v0-1-3_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-v0-1-3_v7
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-v0-1-3-v7 is running
Tearing down inference service cgato-l3-thespice-8b-v0-1-3-v7
Toredown service cgato-l3-thespice-8b-v0-1-3-v7
Pipeline stage ISVCDeleter completed in 5.63s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-1-3-v7/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-1-3-v7_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.65s
cgato-l3-thespice-8b-v0-1-3_v7 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics