submission_id: cgato-thesalt-rp-l3-8b-d_2357_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e1.5.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, '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: 2024-07-02T03:55:53+00:00
model_name: cgato-thesalt-rp-l3-8b-d_2357_v1
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 12305
num_wins: 6591
celo_rating: 1198.2
propriety_score: 0.7102411744145404
propriety_total_count: 5722.0
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_2357_v1
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e1.5.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-01
win_ratio: 0.5356359203575782
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer to finish
Failed to get response for submission neversleep-noromaid-v0-_8068_v108: no entry with id "neversleep-noromaid-v0-_8068_v108" found on database!
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s
Failed to get response for submission neversleep-noromaid-v0-_8068_v107: no entry with id "neversleep-noromaid-v0-_8068_v107" found on database!
Failed to get response for submission neversleep-noromaid-v0-_8068_v105: no entry with id "neversleep-noromaid-v0-_8068_v105" found on database!
Failed to get response for submission neversleep-noromaid-v0-_8068_v105: no entry with id "neversleep-noromaid-v0-_8068_v105" found on database!
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: Downloaded to shared memory in 36.306s
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 79.29it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 93.53it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 134.92it/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-2357-v1-mkmlizer: quantized model in 24.116s
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e1.5.2 in 60.423s
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2357-v1
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2357-v1/config.json
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2357-v1/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2357-v1/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2357-v1/tokenizer.json
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-2357-v1-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-2357-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2357-v1-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-2357-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2357-v1-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-2357-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2357-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-2357-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2357-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-2357-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: Saving duration: 1.427s
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.856s
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2357-v1_reward
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2357-v1_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2357-v1_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2357-v1_reward/config.json
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2357-v1_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2357-v1_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2357-v1_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2357-v1_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer completed after 148.93s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-2357-v1-mkmlizer
Pipeline stage MKMLizer completed in 149.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-2357-v1
Waiting for inference service cgato-thesalt-rp-l3-8b-d-2357-v1 to be ready
Failed to get response for submission neversleep-noromaid-v0-_8068_v105: no entry with id "neversleep-noromaid-v0-_8068_v105" found on database!
Inference service cgato-thesalt-rp-l3-8b-d-2357-v1 ready after 40.199434757232666s
Pipeline stage ISVCDeployer completed in 46.97s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1412808895111084s
Received healthy response to inference request in 1.361128807067871s
Received healthy response to inference request in 1.2825040817260742s
Received healthy response to inference request in 1.2902774810791016s
Received healthy response to inference request in 1.2452929019927979s
5 requests
0 failed requests
5th percentile: 1.2527351379394531
10th percentile: 1.2601773738861084
20th percentile: 1.275061845779419
30th percentile: 1.2840587615966796
40th percentile: 1.2871681213378907
50th percentile: 1.2902774810791016
60th percentile: 1.3186180114746093
70th percentile: 1.346958541870117
80th percentile: 1.5171592235565188
90th percentile: 1.8292200565338135
95th percentile: 1.9852504730224607
99th percentile: 2.1100748062133787
mean time: 1.4640968322753907
Pipeline stage StressChecker completed in 8.23s
cgato-thesalt-rp-l3-8b-d_2357_v1 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_2357_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics