submission_id: cgato-thesalt-rp-l3-8b-d_2881_v4
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.4.2
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'], '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: 2024-07-04T16:10:20+00:00
model_name: cgato-thesalt-rp-l3-8b-d_2881_v4
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 21994
num_wins: 11796
celo_rating: 1208.32
propriety_score: 0.7121918720852765
propriety_total_count: 10507.0
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_2881_v4
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.4.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-04
win_ratio: 0.5363280894789488
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: Downloaded to shared memory in 55.640s
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▌ | 15/291 [00:00<00:01, 149.33it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 155.89it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 160.93it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 165.35it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 88.94it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 105.64it/s] Loading 0: 42%|████▏ | 121/291 [00:00<00:01, 119.29it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 130.98it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 140.72it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 152.36it/s] Loading 0: 66%|██████▋ | 193/291 [00:01<00:01, 93.22it/s] Loading 0: 73%|███████▎ | 211/291 [00:01<00:00, 107.96it/s] Loading 0: 79%|███████▊ | 229/291 [00:01<00:00, 121.28it/s] Loading 0: 85%|████████▍ | 247/291 [00:01<00:00, 132.43it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 141.03it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 145.80it/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-2881-v4-mkmlizer: quantized model in 22.608s
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.4.2 in 78.248s
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v4
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v4/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v4/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v4/config.json
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v4/tokenizer.json
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v4/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-2881-v4-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-2881-v4-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-v4-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-2881-v4-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-v4-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-2881-v4-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-v4-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-2881-v4-mkmlizer: warnings.warn(
Connection pool is full, discarding connection: %s
cgato-thesalt-rp-l3-8b-d-2881-v4-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-2881-v4-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: Saving duration: 0.399s
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 13.284s
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v4_reward
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v4_reward/config.json
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v4_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v4_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v4_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v4_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v4_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v4_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer completed after 176.37s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-2881-v4-mkmlizer
Pipeline stage MKMLizer completed in 177.28s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-2881-v4
Waiting for inference service cgato-thesalt-rp-l3-8b-d-2881-v4 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-2881-v4 ready after 100.53728079795837s
Pipeline stage ISVCDeployer completed in 107.67s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0937623977661133s
Received healthy response to inference request in 1.2832345962524414s
Received healthy response to inference request in 1.2773792743682861s
Received healthy response to inference request in 1.2810931205749512s
Received healthy response to inference request in 1.2439987659454346s
5 requests
0 failed requests
5th percentile: 1.2506748676300048
10th percentile: 1.2573509693145752
20th percentile: 1.270703172683716
30th percentile: 1.2781220436096192
40th percentile: 1.2796075820922852
50th percentile: 1.2810931205749512
60th percentile: 1.2819497108459472
70th percentile: 1.2828063011169433
80th percentile: 1.445340156555176
90th percentile: 1.7695512771606445
95th percentile: 1.9316568374633787
99th percentile: 2.0613412857055664
mean time: 1.4358936309814454
Pipeline stage StressChecker completed in 7.98s
cgato-thesalt-rp-l3-8b-d_2881_v4 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_2881_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics