submission_id: cgato-thesalt-rp-l3-8b-v0-3-2_v5
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-v0.3.2
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'], '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: 2024-06-19T14:53:56+00:00
model_name: cgato-thesalt-rp-l3-8b-v0-3-2_v5
model_group: cgato/TheSalt-RP-L3-8b-v
num_battles: 21947
num_wins: 12010
celo_rating: 1200.42
propriety_score: 0.7171581769436998
propriety_total_count: 10444.0
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-v0-3-2_v5
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-v0.3.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-19
win_ratio: 0.54722741149132
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer to finish
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-v0-3-2-v5-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-v0-3-2-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: Downloaded to shared memory in 31.618s
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:01, 159.96it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 157.76it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 160.95it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 162.11it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 86.06it/s] Loading 0: 34%|███▍ | 100/291 [00:00<00:01, 99.04it/s] Loading 0: 39%|███▉ | 114/291 [00:00<00:01, 106.48it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 118.22it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 130.11it/s] Loading 0: 57%|█████▋ | 166/291 [00:01<00:00, 140.25it/s] Loading 0: 64%|██████▎ | 185/291 [00:01<00:00, 152.61it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:01, 82.85it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 97.80it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 112.41it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 124.47it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 136.10it/s] Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.07it/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-v0-3-2-v5-mkmlizer: quantized model in 23.230s
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-v0.3.2 in 57.353s
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v5
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v5/config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v5/tokenizer_config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v5/special_tokens_map.json
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v5/tokenizer.json
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v5/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-v0-3-2-v5-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-v0-3-2-v5-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v5-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-v0-3-2-v5-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v5-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-v0-3-2-v5-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v5-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-v0-3-2-v5-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: Saving duration: 0.410s
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.340s
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v5_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer completed after 88.57s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-v0-3-2-v5-mkmlizer
Pipeline stage MKMLizer completed in 94.19s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-v0-3-2-v5
Waiting for inference service cgato-thesalt-rp-l3-8b-v0-3-2-v5 to be ready
Inference service cgato-thesalt-rp-l3-8b-v0-3-2-v5 ready after 50.587982177734375s
Pipeline stage ISVCDeployer completed in 58.92s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0700252056121826s
Received healthy response to inference request in 1.0329246520996094s
Received healthy response to inference request in 1.0370898246765137s
Received healthy response to inference request in 1.0413010120391846s
Received healthy response to inference request in 1.03092622756958s
5 requests
0 failed requests
5th percentile: 1.031325912475586
10th percentile: 1.0317255973815918
20th percentile: 1.0325249671936034
30th percentile: 1.0337576866149902
40th percentile: 1.035423755645752
50th percentile: 1.0370898246765137
60th percentile: 1.038774299621582
70th percentile: 1.0404587745666505
80th percentile: 1.2470458507537843
90th percentile: 1.6585355281829834
95th percentile: 1.864280366897583
99th percentile: 2.028876237869263
mean time: 1.242453384399414
Pipeline stage StressChecker completed in 6.83s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cgato-thesalt-rp-l3-8b-v0-3-2_v5 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-v0-3-2_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics