submission_id: cgato-l3-thespice-8b-v0-8-3_v1
developer_uid: c.gato
status: torndown
model_repo: cgato/L3-TheSpice-8b-v0.8.3
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 {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', 'user_template': 'User: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-23T21:52:08+00:00
model_name: cgato-l3-thespice-8b-v0-8-3_v1
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-v0.
num_battles: 8019
num_wins: 4309
celo_rating: 1182.88
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-v0-8-3_v1
ineligible_reason: propriety_total_count < 800
language_model: cgato/L3-TheSpice-8b-v0.8.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-23
win_ratio: 0.5373487966080559
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer to finish
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-v0-8-3-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-v0-8-3-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: Downloaded to shared memory in 19.012s
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 40%|████ | 117/291 [00:01<00:01, 116.61it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 118.92it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 29.60it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: quantized model in 18.567s
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-v0.8.3 in 38.521s
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-8-3-v1
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-8-3-v1/config.json
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-8-3-v1/special_tokens_map.json
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-8-3-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-v0-8-3-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-v0-8-3-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-8-3-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-v0-8-3-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-8-3-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-v0-8-3-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-8-3-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-v0-8-3-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: Saving duration: 0.283s
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.992s
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-8-3-v1_reward
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-8-3-v1_reward/config.json
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-8-3-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-8-3-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-8-3-v1_reward/merges.txt
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-8-3-v1_reward/vocab.json
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-8-3-v1_reward/tokenizer.json
cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-8-3-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer completed after 223.43s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-v0-8-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 227.14s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-v0-8-3-v1
Waiting for inference service cgato-l3-thespice-8b-v0-8-3-v1 to be ready
Inference service cgato-l3-thespice-8b-v0-8-3-v1 ready after 40.58215403556824s
Pipeline stage ISVCDeployer completed in 47.89s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.108342170715332s
Received healthy response to inference request in 1.2656176090240479s
Received healthy response to inference request in 1.2631802558898926s
Received healthy response to inference request in 1.2682514190673828s
Received healthy response to inference request in 1.2651689052581787s
5 requests
0 failed requests
5th percentile: 1.2635779857635498
10th percentile: 1.2639757156372071
20th percentile: 1.2647711753845214
30th percentile: 1.2652586460113526
40th percentile: 1.2654381275177002
50th percentile: 1.2656176090240479
60th percentile: 1.2666711330413818
70th percentile: 1.2677246570587157
80th percentile: 1.436269569396973
90th percentile: 1.7723058700561525
95th percentile: 1.940324020385742
99th percentile: 2.074738540649414
mean time: 1.4341120719909668
Pipeline stage StressChecker completed in 7.75s
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-v0-8-3_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-v0-8-3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-v0-8-3_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-v0-8-3-v1 is running
Tearing down inference service cgato-l3-thespice-8b-v0-8-3-v1
Toredown service cgato-l3-thespice-8b-v0-8-3-v1
Pipeline stage ISVCDeleter completed in 4.84s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-8-3-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-8-3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-8-3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-8-3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-8-3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-8-3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-8-3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-8-3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-8-3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-8-3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-8-3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
admin requested tearing down of cgato-thespice-7b-invert_1522_v1
Running pipeline stage ISVCDeleter
Deleting key cgato-l3-thespice-8b-v0-8-3-v1_reward/vocab.json from bucket guanaco-reward-models
Checking if service cgato-thespice-7b-invert-1522-v1 is running
Pipeline stage MKMLModelDeleter completed in 3.03s
cgato-l3-thespice-8b-v0-8-3_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics