submission_id: cgato-thesalt-rp-l3-8b-d_7046_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.1.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, '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: 2024-06-21T10:50:15+00:00
model_name: cgato-thesalt-rp-l3-8b-d_7046_v1
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 22032
num_wins: 11462
celo_rating: 1203.18
propriety_score: 0.7129807692307693
propriety_total_count: 10400.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030294016.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-thesalt-rp-l3-8b-d_7046_v1
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.1.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-21
win_ratio: 0.5202432824981844
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-7046-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-7046-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: Downloaded to shared memory in 30.617s
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 81.26it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 96.44it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 141.59it/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-7046-v1-mkmlizer: quantized model in 23.049s
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.1.1 in 56.189s
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-7046-v1/config.json
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-7046-v1/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-7046-v1/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-7046-v1/tokenizer.json
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-7046-v1/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-7046-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-7046-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-7046-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-7046-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-7046-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-7046-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-7046-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-7046-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: Saving duration: 0.413s
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.875s
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-7046-v1_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer completed after 83.05s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-7046-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.47s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-7046-v1
Waiting for inference service cgato-thesalt-rp-l3-8b-d-7046-v1 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-7046-v1 ready after 40.27919054031372s
Pipeline stage ISVCDeployer completed in 45.86s
Running pipeline stage StressChecker
%s, retrying in %s seconds...
Received healthy response to inference request in 5.339175701141357s
Received healthy response to inference request in 3.471510887145996s
Received healthy response to inference request in 2.530243158340454s
Received healthy response to inference request in 3.8030271530151367s
Received healthy response to inference request in 1.2066550254821777s
5 requests
0 failed requests
5th percentile: 1.471372652053833
10th percentile: 1.7360902786254884
20th percentile: 2.265525531768799
30th percentile: 2.7184967041015624
40th percentile: 3.0950037956237795
50th percentile: 3.471510887145996
60th percentile: 3.6041173934936523
70th percentile: 3.7367238998413086
80th percentile: 4.110256862640381
90th percentile: 4.724716281890869
95th percentile: 5.031945991516113
99th percentile: 5.277729759216308
mean time: 3.2701223850250245
Pipeline stage StressChecker completed in 37.17s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.05s
cgato-thesalt-rp-l3-8b-d_7046_v1 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_7046_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics