submission_id: cgato-thesalt-rp-l3-8b-d_7805_v3
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.1.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 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': "{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: 2024-06-22T23:10:40+00:00
model_name: cgato-thesalt-rp-l3-8b-d_7805_v3
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 14597
num_wins: 7319
celo_rating: 1202.0
propriety_score: 0.7195174493752693
propriety_total_count: 6963.0
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_7805_v3
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.1.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-22
win_ratio: 0.5014043981640063
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-7805-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-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: Downloaded to shared memory in 25.268s
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 85.94it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 100.29it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 144.80it/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-7805-v3-mkmlizer: quantized model in 18.909s
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.1.2 in 45.173s
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-7805-v3
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-7805-v3/config.json
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-7805-v3/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-7805-v3/tokenizer_config.json
Connection pool is full, discarding connection: %s
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-7805-v3/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-7805-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-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-7805-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-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-7805-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-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-7805-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-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: Saving duration: 0.296s
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 10.871s
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-7805-v3_reward
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-7805-v3_reward/config.json
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-7805-v3_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-7805-v3_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-7805-v3_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-7805-v3_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-7805-v3_reward/tokenizer.json
Job cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer completed after 83.97s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-7805-v3-mkmlizer
Pipeline stage MKMLizer completed in 84.38s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-7805-v3
Waiting for inference service cgato-thesalt-rp-l3-8b-d-7805-v3 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-7805-v3 ready after 140.71828842163086s
Pipeline stage ISVCDeployer completed in 146.46s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.142469882965088s
Received healthy response to inference request in 1.2704107761383057s
Received healthy response to inference request in 1.274745225906372s
Received healthy response to inference request in 1.3011736869812012s
Received healthy response to inference request in 1.2601611614227295s
5 requests
0 failed requests
5th percentile: 1.2622110843658447
10th percentile: 1.26426100730896
20th percentile: 1.2683608531951904
30th percentile: 1.271277666091919
40th percentile: 1.2730114459991455
50th percentile: 1.274745225906372
60th percentile: 1.2853166103363036
70th percentile: 1.2958879947662354
80th percentile: 1.4694329261779786
90th percentile: 1.8059514045715332
95th percentile: 1.9742106437683105
99th percentile: 2.1088180351257324
mean time: 1.4497921466827393
Pipeline stage StressChecker completed in 7.94s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
cgato-thesalt-rp-l3-8b-d_7805_v3 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_7805_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics