submission_id: cgato-thesalt-rp-l3-8b-d_2881_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.4.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 100, '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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|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: 2024-06-25T01:49:12+00:00
model_name: cgato-thesalt-rp-l3-8b-d_2881_v1
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 12648
num_wins: 6813
celo_rating: 1201.5
propriety_score: 0.6991590870087524
propriety_total_count: 5827.0
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-thesalt-rp-l3-8b-d_2881_v1
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.4.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-24
win_ratio: 0.5386622390891841
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-2881-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-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: Downloaded to shared memory in 32.078s
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 77.24it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 84.32it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 124.67it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: quantized model in 24.227s
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v1
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v1/config.json
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v1/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v1/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v1/tokenizer.json
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v1/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-2881-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-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-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-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-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-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-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-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: Saving duration: 0.426s
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.022s
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v1_reward
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v1_reward/config.json
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v1_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v1_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v1_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v1_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v1_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v1_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer completed after 86.73s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-2881-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.19s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-2881-v1
Waiting for inference service cgato-thesalt-rp-l3-8b-d-2881-v1 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-2881-v1 ready after 50.89372205734253s
Pipeline stage ISVCDeployer completed in 56.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1852846145629883s
Received healthy response to inference request in 1.3007140159606934s
Received healthy response to inference request in 1.2881321907043457s
Received healthy response to inference request in 1.3001527786254883s
Received healthy response to inference request in 1.304366111755371s
5 requests
0 failed requests
5th percentile: 1.2905363082885741
10th percentile: 1.2929404258728028
20th percentile: 1.2977486610412599
30th percentile: 1.3002650260925293
40th percentile: 1.3004895210266114
50th percentile: 1.3007140159606934
60th percentile: 1.3021748542785645
70th percentile: 1.3036356925964356
80th percentile: 1.4805498123168948
90th percentile: 1.8329172134399414
95th percentile: 2.009100914001465
99th percentile: 2.1500478744506837
mean time: 1.4757299423217773
Pipeline stage StressChecker completed in 8.14s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cgato-thesalt-rp-l3-8b-d_2881_v1 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_2881_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics