submission_id: cgato-l3-thespice-8b-lun_3374_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-Lunar-Eon-8
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 200, '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': "<|im_start|>system\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}
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': True}
timestamp: 2024-05-20T17:01:23+00:00
model_name: cgato-l3-thespice-8b-lun_3374_v2
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-Lun
num_battles: 21396
num_wins: 11366
celo_rating: 1196.17
safety_score: 0.85
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030277632.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-l3-thespice-8b-lun_3374_v2
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-Lunar-Eon-8
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-20
win_ratio: 0.5312207889325108
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-lun-3374-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-lun-3374-v2-mkmlizer to finish
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-lun-3374-v2-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-lun-3374-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: Downloaded to shared memory in 16.738s
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 80.39it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 90.77it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 131.07it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: quantized model in 19.070s
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-Lunar-Eon-8 in 36.797s
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-lun-3374-v2
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-lun-3374-v2/config.json
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-lun-3374-v2/tokenizer_config.json
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-lun-3374-v2/special_tokens_map.json
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-lun-3374-v2/tokenizer.json
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-lun-3374-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-lun-3374-v2-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-lun-3374-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-lun-3374-v2-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-lun-3374-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-lun-3374-v2-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-lun-3374-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-lun-3374-v2-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-lun-3374-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: Saving duration: 0.233s
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.134s
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v2_reward
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v2_reward/config.json
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v2_reward/merges.txt
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v2_reward/vocab.json
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v2_reward/tokenizer.json
cgato-l3-thespice-8b-lun-3374-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-lun-3374-v2-mkmlizer completed after 66.69s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-lun-3374-v2-mkmlizer
Pipeline stage MKMLizer completed in 69.84s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-lun-3374-v2
Waiting for inference service cgato-l3-thespice-8b-lun-3374-v2 to be ready
Inference service cgato-l3-thespice-8b-lun-3374-v2 ready after 30.32378315925598s
Pipeline stage ISVCDeployer completed in 37.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2060940265655518s
Received healthy response to inference request in 1.325415849685669s
Received healthy response to inference request in 1.2968006134033203s
Received healthy response to inference request in 1.3139944076538086s
Received healthy response to inference request in 1.3152434825897217s
5 requests
0 failed requests
5th percentile: 1.300239372253418
10th percentile: 1.3036781311035157
20th percentile: 1.310555648803711
30th percentile: 1.3142442226409912
40th percentile: 1.3147438526153565
50th percentile: 1.3152434825897217
60th percentile: 1.3193124294281007
70th percentile: 1.3233813762664794
80th percentile: 1.5015514850616456
90th percentile: 1.8538227558135987
95th percentile: 2.029958391189575
99th percentile: 2.1708668994903566
mean time: 1.4915096759796143
Pipeline stage StressChecker completed in 8.08s
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-lun_3374_v2 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-lun_3374_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics