submission_id: cgato-thesalt-rp-l3-8b-d_2881_v2
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': 0.05, '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: 2024-06-30T02:00:18+00:00
model_name: cgato-thesalt-rp-l3-8b-d_2881_v2
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 28570
num_wins: 15542
celo_rating: 1205.6
propriety_score: 0.7065136935603257
propriety_total_count: 13510.0
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_v2
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: 2024-06-29
win_ratio: 0.543997199859993
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-2881-v2-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-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: Downloaded to shared memory in 40.714s
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 128.67it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 148.20it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 152.66it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 156.77it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 83.04it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 89.67it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 106.39it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 120.22it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 130.94it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 139.10it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 93.95it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 101.76it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 115.64it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 127.44it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 136.39it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 142.44it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 9.79it/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-v2-mkmlizer: quantized model in 23.299s
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.4.2 in 66.705s
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v2
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v2/config.json
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v2/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v2/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v2/tokenizer.json
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v2/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-2881-v2-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-v2-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-v2-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-v2-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-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-2881-v2-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-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-2881-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: Saving duration: 0.414s
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.275s
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v2_reward
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v2_reward/config.json
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v2_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v2_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v2_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v2_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v2_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v2_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer completed after 94.09s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-2881-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.94s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-2881-v2
Waiting for inference service cgato-thesalt-rp-l3-8b-d-2881-v2 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-2881-v2 ready after 40.17972946166992s
Pipeline stage ISVCDeployer completed in 47.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2377090454101562s
Received healthy response to inference request in 1.3221204280853271s
Received healthy response to inference request in 1.2854959964752197s
Received healthy response to inference request in 1.2815656661987305s
Received healthy response to inference request in 1.2890980243682861s
5 requests
0 failed requests
5th percentile: 1.2823517322540283
10th percentile: 1.2831377983093262
20th percentile: 1.2847099304199219
30th percentile: 1.286216402053833
40th percentile: 1.2876572132110595
50th percentile: 1.2890980243682861
60th percentile: 1.3023069858551026
70th percentile: 1.315515947341919
80th percentile: 1.505238151550293
90th percentile: 1.8714735984802247
95th percentile: 2.0545913219451903
99th percentile: 2.2010855007171632
mean time: 1.4831978321075439
Pipeline stage StressChecker completed in 8.25s
cgato-thesalt-rp-l3-8b-d_2881_v2 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_2881_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics