submission_id: cgato-thesalt-rp-l3-8b-v0-3-2_v9
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-v0.3.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'You:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
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': False}
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': False}
timestamp: 2024-06-19T19:55:57+00:00
model_name: cgato-thesalt-rp-l3-8b-v0-3-2_v9
model_group: cgato/TheSalt-RP-L3-8b-v
num_battles: 26206
num_wins: 14442
celo_rating: 1204.93
propriety_score: 0.729145211122554
propriety_total_count: 12623.0
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-v0-3-2_v9
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-v0.3.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-19
win_ratio: 0.5510951690452568
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer to finish
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-v0-3-2-v9-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-v0-3-2-v9-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: Downloaded to shared memory in 17.199s
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 136.04it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 152.06it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 157.34it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 158.35it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 86.45it/s] Loading 0: 33%|███▎ | 96/291 [00:00<00:02, 88.45it/s] Loading 0: 37%|███▋ | 107/291 [00:01<00:02, 90.70it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 95.37it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 94.14it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 111.64it/s] Loading 0: 57%|█████▋ | 166/291 [00:01<00:00, 125.39it/s] Loading 0: 63%|██████▎ | 184/291 [00:01<00:00, 138.37it/s] Loading 0: 68%|██████▊ | 199/291 [00:01<00:01, 83.46it/s] Loading 0: 74%|███████▎ | 214/291 [00:02<00:00, 95.73it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 107.80it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 121.66it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 131.57it/s] Loading 0: 98%|█████████▊| 284/291 [00:02<00:00, 143.20it/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-v0-3-2-v9-mkmlizer: quantized model in 23.071s
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-v0.3.2 in 42.823s
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9/special_tokens_map.json
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9/config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9/tokenizer_config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9/tokenizer.json
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-v0-3-2-v9-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-v0-3-2-v9-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v9-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-v0-3-2-v9-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v9-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-v0-3-2-v9-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: Saving duration: 0.403s
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.245s
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9_reward
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9_reward/config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9_reward/merges.txt
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9_reward/vocab.json
cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v9_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer completed after 371.53s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-v0-3-2-v9-mkmlizer
Pipeline stage MKMLizer completed in 376.30s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-v0-3-2-v9
Waiting for inference service cgato-thesalt-rp-l3-8b-v0-3-2-v9 to be ready
Inference service cgato-thesalt-rp-l3-8b-v0-3-2-v9 ready after 80.44658279418945s
Pipeline stage ISVCDeployer completed in 89.55s
Running pipeline stage StressChecker
Received healthy response to inference request in 10.982656478881836s
Received healthy response to inference request in 1.016378402709961s
Received healthy response to inference request in 1.039771556854248s
Received healthy response to inference request in 1.0249357223510742s
Received healthy response to inference request in 1.0341789722442627s
5 requests
0 failed requests
5th percentile: 1.0180898666381837
10th percentile: 1.0198013305664062
20th percentile: 1.0232242584228515
30th percentile: 1.0267843723297119
40th percentile: 1.0304816722869874
50th percentile: 1.0341789722442627
60th percentile: 1.0364160060882568
70th percentile: 1.0386530399322509
80th percentile: 3.0283485412597675
90th percentile: 7.0055025100708015
95th percentile: 8.994079494476317
99th percentile: 10.584941082000732
mean time: 3.019584226608276
Pipeline stage StressChecker completed in 15.75s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cgato-thesalt-rp-l3-8b-v0-3-2_v9 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-v0-3-2_v9 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics