submission_id: cgato-thesalt-rp-l3-8b-d_4432_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.14.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', 'You:'], '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: 2024-07-08T11:53:05+00:00
model_name: cgato-thesalt-rp-l3-8b-d_4432_v2
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 30238
num_wins: 14824
celo_rating: 1199.46
propriety_score: 0.717988097523517
propriety_total_count: 5209.0
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_4432_v2
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.14.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-08
win_ratio: 0.49024406376083074
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: Downloaded to shared memory in 32.882s
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 108.49it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:02, 118.31it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 121.88it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 115.78it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 120.25it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 116.94it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:02, 67.57it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 75.71it/s] Loading 0: 40%|███▉ | 116/291 [00:01<00:02, 86.83it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 95.83it/s] Loading 0: 48%|████▊ | 141/291 [00:01<00:01, 96.77it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 107.41it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 103.54it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:01, 106.49it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 68.33it/s] Loading 0: 70%|███████ | 205/291 [00:02<00:01, 77.88it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 88.85it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 89.84it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 103.65it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 101.88it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 109.38it/s] Loading 0: 98%|█████████▊| 285/291 [00:02<00:00, 108.02it/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-4432-v2-mkmlizer: quantized model in 25.218s
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.14.1 in 58.100s
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-4432-v2
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-4432-v2/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-4432-v2/config.json
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-4432-v2/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-4432-v2/tokenizer.json
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-4432-v2/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: 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-4432-v2-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: 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-4432-v2-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-4432-v2-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-4432-v2-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-4432-v2-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-4432-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4432-v2_reward
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4432-v2_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4432-v2_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4432-v2_reward/config.json
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4432-v2_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4432-v2_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4432-v2_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4432-v2_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer completed after 83.33s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-4432-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.26s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-4432-v2
Waiting for inference service cgato-thesalt-rp-l3-8b-d-4432-v2 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-4432-v2 ready after 40.3568229675293s
Pipeline stage ISVCDeployer completed in 47.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9702987670898438s
Received healthy response to inference request in 1.292637586593628s
Received healthy response to inference request in 1.2837646007537842s
Received healthy response to inference request in 1.302459955215454s
Received healthy response to inference request in 1.2553865909576416s
5 requests
0 failed requests
5th percentile: 1.2610621929168702
10th percentile: 1.2667377948760987
20th percentile: 1.2780889987945556
30th percentile: 1.285539197921753
40th percentile: 1.2890883922576903
50th percentile: 1.292637586593628
60th percentile: 1.2965665340423584
70th percentile: 1.300495481491089
80th percentile: 1.4360277175903322
90th percentile: 1.703163242340088
95th percentile: 1.8367310047149656
99th percentile: 1.9435852146148682
mean time: 1.4209095001220704
Pipeline stage StressChecker completed in 7.79s
cgato-thesalt-rp-l3-8b-d_4432_v2 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_4432_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics