submission_id: cgato-l3-thespice-8b-dpo_4375_v3
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e11.2
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': "{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: 2024-05-28T01:18:01+00:00
model_name: cgato-l3-thespice-8b-dpo_4375_v3
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 6817
num_wins: 3690
celo_rating: 1210.37
safety_score: 0.91
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_4375_v3
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e11.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-27
win_ratio: 0.5412938242628722
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer to finish
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-4375-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-4375-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: Downloaded to shared memory in 20.663s
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 75.87it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 90.00it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 130.65it/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-4375-v3-mkmlizer: quantized model in 22.931s
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e11.2 in 44.857s
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4375-v3/config.json
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4375-v3/special_tokens_map.json
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4375-v3/tokenizer_config.json
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4375-v3/tokenizer.json
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4375-v3/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-4375-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-4375-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-4375-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-4375-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-4375-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-4375-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-4375-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-4375-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: Saving duration: 0.281s
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.083s
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4375-v3_reward
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4375-v3_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4375-v3_reward/config.json
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4375-v3_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4375-v3_reward/merges.txt
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4375-v3_reward/vocab.json
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4375-v3_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4375-v3_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer completed after 135.45s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-4375-v3-mkmlizer
Pipeline stage MKMLizer completed in 137.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-4375-v3
Waiting for inference service cgato-l3-thespice-8b-dpo-4375-v3 to be ready
Inference service cgato-l3-thespice-8b-dpo-4375-v3 ready after 30.169740915298462s
Pipeline stage ISVCDeployer completed in 36.92s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.252262592315674s
Received healthy response to inference request in 1.2466533184051514s
Received healthy response to inference request in 1.258857011795044s
Received healthy response to inference request in 1.2516491413116455s
Received healthy response to inference request in 1.2577736377716064s
5 requests
0 failed requests
5th percentile: 1.2476524829864502
10th percentile: 1.248651647567749
20th percentile: 1.2506499767303467
30th percentile: 1.2528740406036376
40th percentile: 1.255323839187622
50th percentile: 1.2577736377716064
60th percentile: 1.2582069873809814
70th percentile: 1.2586403369903565
80th percentile: 1.4575381278991701
90th percentile: 1.8549003601074219
95th percentile: 2.053581476211548
99th percentile: 2.2125263690948485
mean time: 1.4534391403198241
Pipeline stage StressChecker completed in 7.88s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
cgato-l3-thespice-8b-dpo_4375_v3 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dpo_4375_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics