submission_id: cgato-l3-thespice-8b-dpo_8098_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e18.2
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: 2024-06-05T10:38:35+00:00
model_name: cgato-l3-thespice-8b-dpo_8098_v1
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 12865
num_wins: 6857
celo_rating: 1203.72
safety_score: 0.87
propriety_score: 0.6854219948849105
propriety_total_count: 391.0
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_8098_v1
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e18.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-05
win_ratio: 0.5329965021375825
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer to finish
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-8098-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-8098-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: Downloaded to shared memory in 29.163s
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 64.91it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 76.96it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 111.61it/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-8098-v1-mkmlizer: quantized model in 20.699s
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e18.2 in 51.056s
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8098-v1
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8098-v1/config.json
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8098-v1/tokenizer_config.json
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8098-v1/special_tokens_map.json
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8098-v1/tokenizer.json
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8098-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-8098-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-8098-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-8098-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-8098-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-8098-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-8098-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-8098-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-8098-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: Saving duration: 0.240s
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.214s
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8098-v1_reward
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8098-v1_reward/config.json
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8098-v1_reward/vocab.json
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8098-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8098-v1_reward/merges.txt
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8098-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8098-v1_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8098-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer completed after 72.68s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-8098-v1-mkmlizer
Pipeline stage MKMLizer completed in 73.65s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-8098-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-8098-v1 to be ready
Tearing down inference service cgato-l3-thespice-8b-dpo-8098-v1
%s, retrying in %s seconds...
Creating inference service cgato-l3-thespice-8b-dpo-8098-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-8098-v1 to be ready
Tearing down inference service cgato-l3-thespice-8b-dpo-8098-v1
%s, retrying in %s seconds...
Creating inference service cgato-l3-thespice-8b-dpo-8098-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-8098-v1 to be ready
Inference service cgato-l3-thespice-8b-dpo-8098-v1 ready after 50.395694732666016s
Pipeline stage ISVCDeployer completed in 87.65s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.253089427947998s
Received healthy response to inference request in 1.308196783065796s
Received healthy response to inference request in 1.2711498737335205s
Received healthy response to inference request in 1.281278371810913s
Received healthy response to inference request in 1.2890403270721436s
5 requests
0 failed requests
5th percentile: 1.2731755733489991
10th percentile: 1.2752012729644775
20th percentile: 1.2792526721954345
30th percentile: 1.2828307628631592
40th percentile: 1.2859355449676513
50th percentile: 1.2890403270721436
60th percentile: 1.2967029094696045
70th percentile: 1.3043654918670655
80th percentile: 1.4971753120422364
90th percentile: 1.8751323699951172
95th percentile: 2.0641108989715575
99th percentile: 2.21529372215271
mean time: 1.4805509567260742
Pipeline stage StressChecker completed in 8.04s
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_8098_v1 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_8098_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics