submission_id: chaiml-sao10k-l3-rp-v3-3_v24
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 humor<|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: 2024-07-11T18:49:56+00:00
model_name: chaiml-sao10k-l3-rp-v3-3_v24
model_group: ChaiML/sao10k-l3-rp-v3-3
num_battles: 40674
num_wins: 19837
celo_rating: 1185.54
propriety_score: 0.7104247104247104
propriety_total_count: 5957.0
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_v24
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: 0.48770713477897426
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ Version: 0.8.14 ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: Downloaded to shared memory in 25.761s
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:43, 2.85s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:24, 3.27it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:33, 7.86it/s] Loading 0: 14%|█▍ | 41/291 [00:06<00:18, 13.38it/s] Loading 0: 19%|█▉ | 55/291 [00:06<00:11, 21.09it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:10, 22.32it/s] Loading 0: 27%|██▋ | 78/291 [00:06<00:07, 29.26it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:04, 42.54it/s] Loading 0: 36%|███▋ | 106/291 [00:06<00:03, 51.66it/s] Loading 0: 42%|████▏ | 121/291 [00:07<00:02, 65.72it/s] Loading 0: 46%|████▌ | 133/291 [00:07<00:02, 74.15it/s] Loading 0: 51%|█████ | 148/291 [00:07<00:01, 88.16it/s] Loading 0: 55%|█████▌ | 161/291 [00:07<00:01, 93.96it/s] Loading 0: 59%|█████▉ | 173/291 [00:07<00:02, 54.98it/s] Loading 0: 64%|██████▎ | 185/291 [00:07<00:01, 63.84it/s] Loading 0: 68%|██████▊ | 199/291 [00:08<00:01, 76.76it/s] Loading 0: 73%|███████▎ | 212/291 [00:08<00:00, 85.94it/s] Loading 0: 78%|███████▊ | 226/291 [00:08<00:00, 97.10it/s] Loading 0: 82%|████████▏ | 239/291 [00:08<00:00, 102.04it/s] Loading 0: 87%|████████▋ | 252/291 [00:08<00:00, 107.77it/s] Loading 0: 91%|█████████▏| 266/291 [00:08<00:00, 59.67it/s] Loading 0: 96%|█████████▌| 279/291 [00:09<00:00, 70.51it/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-v24-mkmlizer: quantized model in 30.157s
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 55.918s
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v24
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v24/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v24/config.json
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v24/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v24/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v24/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: loading reward model from ChaiML/gpt2_medium_pairwise_60m_step_937500
chaiml-sao10k-l3-rp-v3-3-v24-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-v24-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v24-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-v24-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v24-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-v24-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v24-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-v24-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: Saving duration: 0.529s
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: Processed model ChaiML/gpt2_medium_pairwise_60m_step_937500 in 4.987s
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v24_reward
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v24_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v24_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v24_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v24_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v24_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v24_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v24_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer completed after 84.01s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v24-mkmlizer
Pipeline stage MKMLizer completed in 84.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v24
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v24 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v24 ready after 40.23851156234741s
Pipeline stage ISVCDeployer completed in 47.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0316686630249023s
Received healthy response to inference request in 1.2604217529296875s
Received healthy response to inference request in 1.2462735176086426s
Received healthy response to inference request in 1.2113945484161377s
Received healthy response to inference request in 1.2400362491607666s
5 requests
0 failed requests
5th percentile: 1.2171228885650636
10th percentile: 1.2228512287139892
20th percentile: 1.2343079090118407
30th percentile: 1.2412837028503418
40th percentile: 1.243778610229492
50th percentile: 1.2462735176086426
60th percentile: 1.2519328117370605
70th percentile: 1.2575921058654784
80th percentile: 1.4146711349487306
90th percentile: 1.7231698989868165
95th percentile: 1.8774192810058592
99th percentile: 2.000818786621094
mean time: 1.3979589462280273
Pipeline stage StressChecker completed in 7.74s
chaiml-sao10k-l3-rp-v3-3_v24 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v24 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics