submission_id: cgato-l3-thespice-8b-v0-5-2_v1
developer_uid: c.gato
status: torndown
model_repo: cgato/L3-TheSpice-8b-v0.5.2
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####\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: 2024-04-20T19:02:39+00:00
model_name: cgato-l3-thespice-8b-v0-5-2_v1
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-v0.
num_battles: 6414
num_wins: 3603
celo_rating: 1191.37
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-v0-5-2_v1
ineligible_reason: propriety_total_count < 800
language_model: cgato/L3-TheSpice-8b-v0.5.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-20
win_ratio: 0.5617399438727783
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer to finish
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-v0-5-2-v1-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-v0-5-2-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: Downloaded to shared memory in 33.804s
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 68.48it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 73.68it/s] Loading 0: 99%|█████████▊| 287/291 [00:09<00:00, 26.00it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: quantized model in 21.451s
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-v0.5.2 in 56.887s
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-5-2-v1
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-5-2-v1/config.json
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-5-2-v1/tokenizer_config.json
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-5-2-v1/special_tokens_map.json
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-5-2-v1/tokenizer.json
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-5-2-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-v0-5-2-v1-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-v0-5-2-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-5-2-v1-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-v0-5-2-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-5-2-v1-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-v0-5-2-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-5-2-v1-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-v0-5-2-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: Saving duration: 0.260s
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.227s
cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-5-2-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer completed after 94.99s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-v0-5-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 100.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-v0-5-2-v1
Waiting for inference service cgato-l3-thespice-8b-v0-5-2-v1 to be ready
Inference service cgato-l3-thespice-8b-v0-5-2-v1 ready after 40.24942898750305s
Pipeline stage ISVCDeployer completed in 48.13s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.107686996459961s
Received healthy response to inference request in 1.2628288269042969s
Received healthy response to inference request in 1.269655466079712s
Received healthy response to inference request in 1.2753558158874512s
Received healthy response to inference request in 1.2847716808319092s
5 requests
0 failed requests
5th percentile: 1.2641941547393798
10th percentile: 1.265559482574463
20th percentile: 1.268290138244629
30th percentile: 1.2707955360412597
40th percentile: 1.2730756759643556
50th percentile: 1.2753558158874512
60th percentile: 1.2791221618652344
70th percentile: 1.2828885078430177
80th percentile: 1.4493547439575196
90th percentile: 1.7785208702087403
95th percentile: 1.9431039333343505
99th percentile: 2.074770383834839
mean time: 1.440059757232666
Pipeline stage StressChecker completed in 7.87s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Retrying (%r) after connection broken by '%r': %s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.07s
cgato-l3-thespice-8b-v0-5-2_v1 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-v0-5-2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-v0-5-2_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-v0-5-2-v1 is running
Tearing down inference service cgato-l3-thespice-8b-v0-5-2-v1
Toredown service cgato-l3-thespice-8b-v0-5-2-v1
Pipeline stage ISVCDeleter completed in 6.40s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-5-2-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-5-2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-5-2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-5-2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-5-2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-5-2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-5-2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-5-2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-5-2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-5-2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-5-2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-5-2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.89s
cgato-l3-thespice-8b-v0-5-2_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics