submission_id: chaiml-sao10k-l3-rp-v3-3_v9
developer_uid: robert_irvine
status: inactive
model_repo: ChaiML/sao10k-l3-rp-v3-3
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
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: 2024-07-10T18:40:43+00:00
model_name: chaiml-sao10k-l3-rp-v3-3_v9
model_group: ChaiML/sao10k-l3-rp-v3-3
num_battles: 33323
num_wins: 18005
celo_rating: 1200.16
propriety_score: 0.7232413178984862
propriety_total_count: 5615.0
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_v9
ineligible_reason: None
language_model: ChaiML/sao10k-l3-rp-v3-3
model_size: 8B
reward_model: ChaiML/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-07-10
win_ratio: 0.5403174984245116
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ Version: 0.8.14 ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: Downloaded to shared memory in 25.935s
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:33, 2.82s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:23, 3.30it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:33, 7.94it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.52it/s] Loading 0: 19%|█▉ | 55/291 [00:06<00:11, 21.28it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:10, 21.87it/s] Loading 0: 27%|██▋ | 78/291 [00:06<00:07, 28.60it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:04, 41.38it/s] Loading 0: 36%|███▌ | 105/291 [00:06<00:03, 49.32it/s] Loading 0: 42%|████▏ | 121/291 [00:07<00:02, 65.29it/s] Loading 0: 46%|████▌ | 133/291 [00:07<00:02, 73.47it/s] Loading 0: 51%|█████ | 148/291 [00:07<00:01, 86.39it/s] Loading 0: 55%|█████▌ | 161/291 [00:07<00:01, 92.33it/s] Loading 0: 59%|█████▉ | 173/291 [00:07<00:02, 52.53it/s] Loading 0: 64%|██████▎ | 185/291 [00:07<00:01, 61.66it/s] Loading 0: 68%|██████▊ | 199/291 [00:08<00:01, 74.75it/s] Loading 0: 73%|███████▎ | 211/291 [00:08<00:00, 82.83it/s] Loading 0: 76%|███████▋ | 222/291 [00:08<00:00, 83.54it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 97.91it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:00, 100.40it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 111.43it/s] Loading 0: 96%|█████████▌| 278/291 [00:09<00:00, 56.81it/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-v9-mkmlizer: quantized model in 29.806s
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 55.741s
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v9
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v9/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v9/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v9/config.json
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v9/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v9/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v9-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-v9-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-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.
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.05s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.06s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.51s/it]
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.56it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.58it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.35it/s]
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: Saving duration: 2.194s
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.177s
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v9_reward
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v9_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v9_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v9_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v9_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v9_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v9_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v9_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer completed after 107.07s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v9-mkmlizer
Pipeline stage MKMLizer completed in 108.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v9
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v9 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v9 ready after 50.24773955345154s
Pipeline stage ISVCDeployer completed in 57.34s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0385870933532715s
Received healthy response to inference request in 1.255951166152954s
Received healthy response to inference request in 1.285801649093628s
Received healthy response to inference request in 1.2357172966003418s
Received healthy response to inference request in 1.2574639320373535s
5 requests
0 failed requests
5th percentile: 1.2397640705108643
10th percentile: 1.2438108444213867
20th percentile: 1.2519043922424316
30th percentile: 1.256253719329834
40th percentile: 1.2568588256835938
50th percentile: 1.2574639320373535
60th percentile: 1.2687990188598632
70th percentile: 1.280134105682373
80th percentile: 1.4363587379455567
90th percentile: 1.7374729156494142
95th percentile: 1.8880300045013427
99th percentile: 2.008475675582886
mean time: 1.4147042274475097
Pipeline stage StressChecker completed in 8.39s
chaiml-sao10k-l3-rp-v3-3_v9 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v9 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics