submission_id: cgato-thesalt-rp-l3-8b-d_9303_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.2.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.9, '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: 2024-06-22T23:21:22+00:00
model_name: cgato-thesalt-rp-l3-8b-d_9303_v1
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 34731
num_wins: 18184
celo_rating: 1203.75
propriety_score: 0.7099403820416109
propriety_total_count: 16438.0
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_9303_v1
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.2.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-22
win_ratio: 0.523566842302266
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-9303-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-9303-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: Downloaded to shared memory in 34.900s
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 76.62it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 93.45it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 137.06it/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-9303-v1-mkmlizer: quantized model in 23.665s
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.2.1 in 61.123s
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9303-v1
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9303-v1/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9303-v1/config.json
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9303-v1/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9303-v1/tokenizer.json
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9303-v1/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-9303-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-9303-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-9303-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-9303-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-9303-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-9303-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-9303-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-9303-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: Saving duration: 0.419s
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.148s
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9303-v1_reward
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9303-v1_reward/config.json
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9303-v1_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9303-v1_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9303-v1_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9303-v1_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9303-v1_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9303-v1_reward/reward.tensors
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Job cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer completed after 93.5s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-9303-v1-mkmlizer
Pipeline stage MKMLizer completed in 93.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-9303-v1
Waiting for inference service cgato-thesalt-rp-l3-8b-d-9303-v1 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-9303-v1 ready after 40.31084752082825s
Pipeline stage ISVCDeployer completed in 46.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.24371600151062s
Received healthy response to inference request in 1.317021131515503s
Received healthy response to inference request in 1.2987594604492188s
Received healthy response to inference request in 1.2992289066314697s
Received healthy response to inference request in 1.2798047065734863s
5 requests
0 failed requests
5th percentile: 1.283595657348633
10th percentile: 1.2873866081237793
20th percentile: 1.2949685096740722
30th percentile: 1.298853349685669
40th percentile: 1.2990411281585694
50th percentile: 1.2992289066314697
60th percentile: 1.306345796585083
70th percentile: 1.3134626865386962
80th percentile: 1.5023601055145266
90th percentile: 1.8730380535125732
95th percentile: 2.0583770275115967
99th percentile: 2.2066482067108155
mean time: 1.4877060413360597
Pipeline stage StressChecker completed in 8.23s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
cgato-thesalt-rp-l3-8b-d_9303_v1 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_9303_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics