submission_id: cgato-l3-thespice-8b-dpo_2837_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e14.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, '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{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{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: 2024-06-02T04:58:58+00:00
model_name: cgato-l3-thespice-8b-dpo_2837_v1
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 8644
num_wins: 4571
celo_rating: 1212.69
safety_score: 0.85
propriety_score: 0.6101694915254238
propriety_total_count: 177.0
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-dpo_2837_v1
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e14.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5288061082832022
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer to finish
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-2837-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-dpo-2837-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: Downloaded to shared memory in 32.056s
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 79.40it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 92.23it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 135.63it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: quantized model in 23.496s
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2837-v1
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2837-v1/tokenizer_config.json
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2837-v1/special_tokens_map.json
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2837-v1/config.json
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2837-v1/tokenizer.json
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2837-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-2837-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-dpo-2837-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-2837-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-dpo-2837-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-2837-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-dpo-2837-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-2837-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-dpo-2837-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: Saving duration: 0.452s
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.959s
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2837-v1_reward
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2837-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2837-v1_reward/config.json
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2837-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2837-v1_reward/vocab.json
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2837-v1_reward/merges.txt
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2837-v1_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2837-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer completed after 83.49s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-2837-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.47s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-2837-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-2837-v1 to be ready
Inference service cgato-l3-thespice-8b-dpo-2837-v1 ready after 40.22241473197937s
Pipeline stage ISVCDeployer completed in 47.45s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2542474269866943s
Received healthy response to inference request in 1.3127155303955078s
Received healthy response to inference request in 1.306251049041748s
Received healthy response to inference request in 1.3154876232147217s
Received healthy response to inference request in 1.2768754959106445s
5 requests
0 failed requests
5th percentile: 1.2827506065368652
10th percentile: 1.288625717163086
20th percentile: 1.3003759384155273
30th percentile: 1.3075439453125
40th percentile: 1.310129737854004
50th percentile: 1.3127155303955078
60th percentile: 1.3138243675231933
70th percentile: 1.3149332046508788
80th percentile: 1.5032395839691164
90th percentile: 1.8787435054779054
95th percentile: 2.0664954662322996
99th percentile: 2.2166970348358155
mean time: 1.4931154251098633
Pipeline stage StressChecker completed in 8.06s
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 0.02s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dpo_2837_v1 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_2837_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics