submission_id: cgato-thesalt-rp-l3-8b-d_9086_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.3.1
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: 2024-06-24T21:14:33+00:00
model_name: cgato-thesalt-rp-l3-8b-d_9086_v1
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 35028
num_wins: 18912
celo_rating: 1199.46
propriety_score: 0.726155894456548
propriety_total_count: 16524.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030277632.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-thesalt-rp-l3-8b-d_9086_v1
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.3.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-24
win_ratio: 0.539910928400137
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-9086-v1-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-9086-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: Downloaded to shared memory in 34.254s
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 72.97it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 86.96it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 126.74it/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-9086-v1-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.3.1 in 60.511s
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9086-v1
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9086-v1/config.json
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9086-v1/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9086-v1/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9086-v1/tokenizer.json
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9086-v1/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-9086-v1-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-9086-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-9086-v1-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-9086-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-9086-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-9086-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-9086-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-9086-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: Saving duration: 0.396s
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.433s
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9086-v1_reward
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9086-v1_reward/config.json
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9086-v1_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9086-v1_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9086-v1_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9086-v1_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9086-v1_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9086-v1_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer completed after 84.16s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-9086-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.45s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-9086-v1
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Waiting for inference service cgato-thesalt-rp-l3-8b-d-9086-v1 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-9086-v1 ready after 40.26844072341919s
Pipeline stage ISVCDeployer completed in 46.01s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.221778631210327s
Received healthy response to inference request in 1.3057968616485596s
Received healthy response to inference request in 1.2878618240356445s
Received healthy response to inference request in 1.309981107711792s
Received healthy response to inference request in 1.265465259552002s
5 requests
0 failed requests
5th percentile: 1.2699445724487304
10th percentile: 1.274423885345459
20th percentile: 1.283382511138916
30th percentile: 1.2914488315582275
40th percentile: 1.2986228466033936
50th percentile: 1.3057968616485596
60th percentile: 1.3074705600738525
70th percentile: 1.3091442584991455
80th percentile: 1.4923406124114993
90th percentile: 1.8570596218109132
95th percentile: 2.03941912651062
99th percentile: 2.1853067302703857
mean time: 1.478176736831665
Pipeline stage StressChecker completed in 8.30s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
cgato-thesalt-rp-l3-8b-d_9086_v1 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_9086_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics