submission_id: cgato-thesalt-rp-l3-8b-d_2881_v3
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': 1.0, 'top_p': 1.0, 'min_p': 0.0, '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: 2024-06-30T16:33:31+00:00
model_name: cgato-thesalt-rp-l3-8b-d_2881_v3
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 20699
num_wins: 10799
celo_rating: 1200.95
propriety_score: 0.718358395989975
propriety_total_count: 9576.0
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_v3
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: 2024-06-30
win_ratio: 0.5217160249287405
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-2881-v3-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-d-2881-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
Retrying (%r) after connection broken by '%r': %s
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 100.10it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:03, 86.49it/s] Loading 0: 12%|█▏ | 36/291 [00:00<00:02, 101.08it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:02, 102.84it/s] Loading 0: 20%|██ | 59/291 [00:00<00:02, 93.84it/s] Loading 0: 24%|██▍ | 71/291 [00:00<00:02, 100.57it/s] Loading 0: 28%|██▊ | 82/291 [00:00<00:02, 102.83it/s] Loading 0: 32%|███▏ | 93/291 [00:01<00:03, 56.72it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 63.88it/s] Loading 0: 40%|███▉ | 116/291 [00:01<00:02, 76.95it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 88.65it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 89.53it/s] Loading 0: 52%|█████▏ | 152/291 [00:01<00:01, 95.19it/s] Loading 0: 56%|█████▌ | 163/291 [00:01<00:01, 97.82it/s] Loading 0: 60%|█████▉ | 174/291 [00:01<00:01, 95.74it/s] Loading 0: 64%|██████▎ | 185/291 [00:02<00:01, 95.59it/s] Loading 0: 67%|██████▋ | 195/291 [00:02<00:01, 56.68it/s] Loading 0: 72%|███████▏ | 210/291 [00:02<00:01, 72.30it/s] Loading 0: 76%|███████▌ | 221/291 [00:02<00:00, 76.46it/s] Loading 0: 80%|████████ | 234/291 [00:02<00:00, 87.26it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 93.35it/s] Loading 0: 88%|████████▊ | 257/291 [00:03<00:00, 91.12it/s] Loading 0: 93%|█████████▎| 270/291 [00:03<00:00, 100.56it/s] Loading 0: 97%|█████████▋| 281/291 [00:03<00:00, 101.81it/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-v3-mkmlizer: quantized model in 25.140s
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.4.2 in 70.631s
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v3
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v3/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v3/config.json
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v3/tokenizer.json
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v3/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v3/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-2881-v3-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-d-2881-v3-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-v3-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-d-2881-v3-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-v3-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-v3-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-v3-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-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: Saving duration: 0.457s
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.528s
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v3_reward
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v3_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v3_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v3_reward/config.json
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v3_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v3_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v3_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v3_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer completed after 124.0s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-2881-v3-mkmlizer
Pipeline stage MKMLizer completed in 124.83s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-2881-v3
Waiting for inference service cgato-thesalt-rp-l3-8b-d-2881-v3 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-2881-v3 ready after 40.29852652549744s
Pipeline stage ISVCDeployer completed in 47.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.282968044281006s
Received healthy response to inference request in 1.2983992099761963s
Received healthy response to inference request in 1.294144630432129s
Received healthy response to inference request in 1.2887639999389648s
Received healthy response to inference request in 1.2556836605072021s
5 requests
0 failed requests
5th percentile: 1.2622997283935546
10th percentile: 1.2689157962799071
20th percentile: 1.2821479320526123
30th percentile: 1.2898401260375976
40th percentile: 1.2919923782348632
50th percentile: 1.294144630432129
60th percentile: 1.2958464622497559
70th percentile: 1.2975482940673828
80th percentile: 1.4953129768371585
90th percentile: 1.8891405105590822
95th percentile: 2.0860542774200437
99th percentile: 2.2435852909088134
mean time: 1.4839919090270997
Pipeline stage StressChecker completed in 8.05s
cgato-thesalt-rp-l3-8b-d_2881_v3 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_2881_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics