submission_id: cgato-l3-thespice-8b-dpo_5102_v3
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e12.3
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': "{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}
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: 2024-05-29T03:47:33+00:00
model_name: cgato-l3-thespice-8b-dpo_5102_v3
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 12498
num_wins: 7033
celo_rating: 1213.15
safety_score: 0.89
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_5102_v3
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e12.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-28
win_ratio: 0.562730036805889
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer to finish
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-5102-v3-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-5102-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 82.86it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 98.06it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 139.76it/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-5102-v3-mkmlizer: quantized model in 23.308s
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e12.3 in 43.198s
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v3
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v3/config.json
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v3/tokenizer_config.json
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v3/special_tokens_map.json
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v3/tokenizer.json
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v3/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-5102-v3-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-5102-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5102-v3-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-5102-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5102-v3-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-5102-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5102-v3-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-5102-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: Saving duration: 0.393s
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.259s
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v3_reward
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v3_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v3_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v3_reward/config.json
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v3_reward/vocab.json
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v3_reward/merges.txt
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v3_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v3_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer completed after 63.52s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-5102-v3-mkmlizer
Pipeline stage MKMLizer completed in 67.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-5102-v3
Waiting for inference service cgato-l3-thespice-8b-dpo-5102-v3 to be ready
Inference service cgato-l3-thespice-8b-dpo-5102-v3 ready after 40.301613330841064s
Pipeline stage ISVCDeployer completed in 47.70s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.271852731704712s
Received healthy response to inference request in 1.2307398319244385s
Received healthy response to inference request in 1.239659070968628s
Received healthy response to inference request in 1.266702651977539s
Received healthy response to inference request in 1.2536113262176514s
5 requests
0 failed requests
5th percentile: 1.2325236797332764
10th percentile: 1.2343075275421143
20th percentile: 1.23787522315979
30th percentile: 1.2424495220184326
40th percentile: 1.248030424118042
50th percentile: 1.2536113262176514
60th percentile: 1.2588478565216064
70th percentile: 1.2640843868255616
80th percentile: 1.4677326679229739
90th percentile: 1.8697926998138428
95th percentile: 2.0708227157592773
99th percentile: 2.231646728515625
mean time: 1.4525131225585937
Pipeline stage StressChecker completed in 7.85s
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-dpo_5102_v3 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_5102_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics