submission_id: cgato-l3-thespice-8b-dpo_7976_v3
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e19.2
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', '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: 2024-06-07T02:03:57+00:00
model_name: cgato-l3-thespice-8b-dpo_7976_v3
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 11303
num_wins: 5928
celo_rating: 1208.52
safety_score: 0.85
propriety_score: 0.6829573934837093
propriety_total_count: 798.0
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_7976_v3
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e19.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-06
win_ratio: 0.5244625320711316
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer to finish
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-7976-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-7976-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: Downloaded to shared memory in 15.431s
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 92.34it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:00, 107.51it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 154.55it/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-7976-v3-mkmlizer: quantized model in 17.232s
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e19.2 in 33.710s
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7976-v3
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7976-v3/special_tokens_map.json
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7976-v3/config.json
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7976-v3/tokenizer_config.json
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7976-v3/tokenizer.json
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7976-v3/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-7976-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-7976-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-7976-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-7976-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-7976-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-7976-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-7976-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-7976-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: Saving duration: 0.230s
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.662s
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v3_reward
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v3_reward/config.json
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v3_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v3_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v3_reward/merges.txt
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v3_reward/vocab.json
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v3_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v3_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer completed after 62.84s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-7976-v3-mkmlizer
Pipeline stage MKMLizer completed in 63.48s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-7976-v3
Waiting for inference service cgato-l3-thespice-8b-dpo-7976-v3 to be ready
Inference service cgato-l3-thespice-8b-dpo-7976-v3 ready after 40.27594709396362s
Pipeline stage ISVCDeployer completed in 46.09s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1489431858062744s
Received healthy response to inference request in 1.3164029121398926s
Received healthy response to inference request in 1.5303435325622559s
Received healthy response to inference request in 1.3248960971832275s
Received healthy response to inference request in 1.3221251964569092s
5 requests
0 failed requests
5th percentile: 1.317547369003296
10th percentile: 1.3186918258666993
20th percentile: 1.3209807395935058
30th percentile: 1.322679376602173
40th percentile: 1.3237877368927002
50th percentile: 1.3248960971832275
60th percentile: 1.4070750713348388
70th percentile: 1.4892540454864502
80th percentile: 1.6540634632110596
90th percentile: 1.901503324508667
95th percentile: 2.0252232551574707
99th percentile: 2.1241991996765135
mean time: 1.5285421848297118
Pipeline stage StressChecker completed in 8.24s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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_7976_v3 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_7976_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics