submission_id: cgato-thesalt-rp-l3-8b-v0-3-2_v6
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}\n', 'prompt_template': '{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: 2024-06-19T15:41:26+00:00
model_name: cgato-thesalt-rp-l3-8b-v0-3-2_v6
model_group: cgato/TheSalt-RP-L3-8b-v
num_battles: 23536
num_wins: 14799
celo_rating: 1201.98
propriety_score: 0.7064958020326999
propriety_total_count: 11315.0
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_v6
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: 0.628781441196465
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer to finish
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-v0-3-2-v6-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-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: Downloaded to shared memory in 45.468s
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 3%|▎ | 9/291 [00:00<00:03, 87.03it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:02, 94.25it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 89.69it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:02, 87.70it/s] Loading 0: 18%|█▊ | 53/291 [00:00<00:02, 97.51it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:02, 100.50it/s] Loading 0: 26%|██▋ | 77/291 [00:00<00:02, 92.98it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:04, 41.50it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:04, 45.23it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:03, 51.09it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:03, 58.45it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:02, 64.72it/s] Loading 0: 45%|████▌ | 132/291 [00:01<00:02, 72.53it/s] Loading 0: 49%|████▉ | 143/291 [00:02<00:01, 80.73it/s] Loading 0: 53%|█████▎ | 153/291 [00:02<00:01, 85.31it/s] Loading 0: 57%|█████▋ | 165/291 [00:02<00:01, 91.49it/s] Loading 0: 60%|██████ | 176/291 [00:02<00:01, 96.08it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 52.62it/s] Loading 0: 67%|██████▋ | 195/291 [00:02<00:01, 54.68it/s] Loading 0: 71%|███████ | 207/291 [00:03<00:01, 66.29it/s] Loading 0: 75%|███████▌ | 219/291 [00:03<00:00, 74.96it/s] Loading 0: 79%|███████▊ | 229/291 [00:03<00:00, 77.99it/s] Loading 0: 82%|████████▏ | 239/291 [00:03<00:00, 80.11it/s] Loading 0: 86%|████████▋ | 251/291 [00:03<00:00, 89.41it/s] Loading 0: 91%|█████████ | 264/291 [00:03<00:00, 94.28it/s] Loading 0: 94%|█████████▍| 274/291 [00:03<00:00, 91.77it/s] Loading 0: 98%|█████████▊| 284/291 [00:03<00:00, 93.46it/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-v6-mkmlizer: quantized model in 27.525s
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-v0.3.2 in 76.256s
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6/config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6/special_tokens_map.json
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6/tokenizer_config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6/tokenizer.json
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-v0-3-2-v6-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-v6-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v6-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-v6-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v6-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-v6-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v6-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-v6-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: Saving duration: 0.492s
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.383s
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6_reward
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6_reward/config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6_reward/vocab.json
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6_reward/merges.txt
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v6_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer completed after 113.87s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-v0-3-2-v6-mkmlizer
Pipeline stage MKMLizer completed in 118.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-v0-3-2-v6
Waiting for inference service cgato-thesalt-rp-l3-8b-v0-3-2-v6 to be ready
Inference service cgato-thesalt-rp-l3-8b-v0-3-2-v6 ready after 50.303481101989746s
Pipeline stage ISVCDeployer completed in 58.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8805792331695557s
Received healthy response to inference request in 1.0437042713165283s
Received healthy response to inference request in 1.0325982570648193s
Received healthy response to inference request in 1.0468392372131348s
Received healthy response to inference request in 1.0230257511138916s
5 requests
0 failed requests
5th percentile: 1.0249402523040771
10th percentile: 1.0268547534942627
20th percentile: 1.0306837558746338
30th percentile: 1.0348194599151612
40th percentile: 1.0392618656158448
50th percentile: 1.0437042713165283
60th percentile: 1.0449582576751708
70th percentile: 1.0462122440338135
80th percentile: 1.2135872364044191
90th percentile: 1.5470832347869874
95th percentile: 1.7138312339782713
99th percentile: 1.8472296333312987
mean time: 1.2053493499755858
Pipeline stage StressChecker completed in 6.66s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cgato-thesalt-rp-l3-8b-v0-3-2_v6 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-v0-3-2_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics