submission_id: chaiml-sao10k-l3-rp-v3-3_v26
developer_uid: robert_irvine
status: inactive
model_repo: ChaiML/sao10k-l3-rp-v3-3
reward_repo: ChaiML/gpt2_medium_pairwise_60m_step_937500
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>system<|end_header_id|>\n\nrespond with a personal question<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': '""', 'prompt_template': '""', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-07-11T18:52:30+00:00
model_name: chaiml-sao10k-l3-rp-v3-3_v26
model_group: ChaiML/sao10k-l3-rp-v3-3
num_battles: 40495
num_wins: 20348
celo_rating: 1195.79
propriety_score: 0.7083196855551916
propriety_total_count: 6106.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-sao10k-l3-rp-v3-3_v26
ineligible_reason: None
language_model: ChaiML/sao10k-l3-rp-v3-3
model_size: 8B
reward_model: ChaiML/gpt2_medium_pairwise_60m_step_937500
us_pacific_date: 2024-07-11
win_ratio: 0.5024817878750463
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ Version: 0.8.14 ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: Downloaded to shared memory in 24.305s
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:30, 2.81s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:23, 3.32it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:32, 7.98it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.61it/s] Loading 0: 19%|█▉ | 55/291 [00:06<00:11, 21.43it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:09, 22.55it/s] Loading 0: 27%|██▋ | 78/291 [00:06<00:07, 29.51it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:04, 42.99it/s] Loading 0: 36%|███▋ | 106/291 [00:06<00:03, 52.52it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 67.19it/s] Loading 0: 46%|████▌ | 134/291 [00:07<00:02, 76.42it/s] Loading 0: 51%|█████ | 148/291 [00:07<00:01, 88.89it/s] Loading 0: 55%|█████▌ | 161/291 [00:07<00:01, 96.30it/s] Loading 0: 60%|█████▉ | 174/291 [00:07<00:02, 57.44it/s] Loading 0: 64%|██████▎ | 185/291 [00:07<00:01, 65.10it/s] Loading 0: 68%|██████▊ | 199/291 [00:07<00:01, 78.69it/s] Loading 0: 73%|███████▎ | 212/291 [00:08<00:00, 87.66it/s] Loading 0: 77%|███████▋ | 224/291 [00:08<00:00, 94.50it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 104.15it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:00, 105.38it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 116.37it/s] Loading 0: 96%|█████████▌| 278/291 [00:08<00:00, 58.73it/s] Loading 0: 99%|█████████▉| 289/291 [00:09<00:00, 66.38it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: quantized model in 29.950s
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 54.256s
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v26
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v26/config.json
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v26/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v26/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v26/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v26/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: loading reward model from ChaiML/gpt2_medium_pairwise_60m_step_937500
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v26-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.
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: Saving duration: 0.528s
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: Processed model ChaiML/gpt2_medium_pairwise_60m_step_937500 in 4.945s
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v26_reward
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v26_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v26_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v26_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v26_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v26_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v26_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v26_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer completed after 95.27s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v26-mkmlizer
Pipeline stage MKMLizer completed in 96.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v26
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v26 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v26 ready after 40.28038430213928s
Pipeline stage ISVCDeployer completed in 47.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8972339630126953s
Received healthy response to inference request in 1.2172152996063232s
Received healthy response to inference request in 1.2500905990600586s
Received healthy response to inference request in 1.199540615081787s
Received healthy response to inference request in 1.2144091129302979s
5 requests
0 failed requests
5th percentile: 1.2025143146514892
10th percentile: 1.2054880142211915
20th percentile: 1.2114354133605958
30th percentile: 1.214970350265503
40th percentile: 1.216092824935913
50th percentile: 1.2172152996063232
60th percentile: 1.2303654193878173
70th percentile: 1.2435155391693116
80th percentile: 1.379519271850586
90th percentile: 1.6383766174316408
95th percentile: 1.767805290222168
99th percentile: 1.87134822845459
mean time: 1.3556979179382325
Pipeline stage StressChecker completed in 7.58s
chaiml-sao10k-l3-rp-v3-3_v26 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v26 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics