submission_id: cgato-l3-thespice-8b-dpo_4355_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e9.1
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', 'You:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s Persona: {memory}\n", 'prompt_template': '***\n{prompt}\n***<|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: 2024-05-24T00:39:36+00:00
model_name: cgato-l3-thespice-8b-dpo_4355_v2
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 8029
num_wins: 4191
celo_rating: 1196.64
safety_score: 0.9
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-dpo_4355_v2
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e9.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-23
win_ratio: 0.5219828123053929
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer to finish
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-4355-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-dpo-4355-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: Downloaded to shared memory in 19.331s
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 83.10it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 97.18it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 140.35it/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-4355-v2-mkmlizer: quantized model in 23.253s
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e9.1 in 45.066s
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4355-v2
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4355-v2/special_tokens_map.json
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4355-v2/config.json
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4355-v2/tokenizer_config.json
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4355-v2/tokenizer.json
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-4355-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-dpo-4355-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-4355-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-dpo-4355-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-4355-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-dpo-4355-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-4355-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-dpo-4355-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: Saving duration: 0.406s
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.270s
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4355-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer completed after 73.68s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-4355-v2-mkmlizer
Pipeline stage MKMLizer completed in 78.17s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-4355-v2
Waiting for inference service cgato-l3-thespice-8b-dpo-4355-v2 to be ready
Inference service cgato-l3-thespice-8b-dpo-4355-v2 ready after 40.2412223815918s
Pipeline stage ISVCDeployer completed in 47.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2794864177703857s
Received healthy response to inference request in 1.3374571800231934s
Received healthy response to inference request in 1.3134453296661377s
Received healthy response to inference request in 1.306025743484497s
Received healthy response to inference request in 1.2857115268707275s
5 requests
0 failed requests
5th percentile: 1.2897743701934814
10th percentile: 1.2938372135162353
20th percentile: 1.3019629001617432
30th percentile: 1.3075096607208252
40th percentile: 1.3104774951934814
50th percentile: 1.3134453296661377
60th percentile: 1.32305006980896
70th percentile: 1.3326548099517823
80th percentile: 1.525863027572632
90th percentile: 1.9026747226715088
95th percentile: 2.091080570220947
99th percentile: 2.241805248260498
mean time: 1.5044252395629882
Pipeline stage StressChecker completed in 8.10s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dpo_4355_v2 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_4355_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics