submission_id: chaiml-sao10k-l3-rp-v3-3_v12
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 excitement<|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: 2024-07-11T17:28:20+00:00
model_name: chaiml-sao10k-l3-rp-v3-3_v12
model_group: ChaiML/sao10k-l3-rp-v3-3
num_battles: 36827
num_wins: 20111
celo_rating: 1223.34
propriety_score: 0.7185840707964601
propriety_total_count: 5085.0
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_v12
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: 2024-07-11
win_ratio: 0.5460938984983843
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ Version: 0.8.14 ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: Downloaded to shared memory in 25.372s
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:37, 2.83s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:24, 3.29it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:33, 7.93it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.48it/s] Loading 0: 19%|█▉ | 55/291 [00:06<00:11, 21.24it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:10, 22.36it/s] Loading 0: 26%|██▋ | 77/291 [00:06<00:07, 28.55it/s] Loading 0: 30%|██▉ | 87/291 [00:06<00:05, 35.34it/s] Loading 0: 35%|███▍ | 101/291 [00:06<00:03, 48.56it/s] Loading 0: 39%|███▉ | 113/291 [00:07<00:03, 57.95it/s] Loading 0: 44%|████▎ | 127/291 [00:07<00:02, 72.14it/s] Loading 0: 48%|████▊ | 140/291 [00:07<00:01, 81.86it/s] Loading 0: 53%|█████▎ | 153/291 [00:07<00:01, 92.08it/s] Loading 0: 57%|█████▋ | 166/291 [00:07<00:02, 54.19it/s] Loading 0: 60%|██████ | 176/291 [00:07<00:01, 61.16it/s] Loading 0: 65%|██████▍ | 189/291 [00:07<00:01, 72.96it/s] Loading 0: 69%|██████▉ | 202/291 [00:08<00:01, 83.75it/s] Loading 0: 73%|███████▎ | 213/291 [00:08<00:00, 86.32it/s] Loading 0: 79%|███████▊ | 229/291 [00:08<00:00, 101.11it/s] Loading 0: 83%|████████▎ | 241/291 [00:08<00:00, 103.97it/s] Loading 0: 88%|████████▊ | 256/291 [00:08<00:00, 115.01it/s] Loading 0: 92%|█████████▏| 269/291 [00:09<00:00, 59.46it/s] Loading 0: 97%|█████████▋| 283/291 [00:09<00:00, 71.10it/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-v12-mkmlizer: quantized model in 29.174s
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 54.546s
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v12
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v12/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v12/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v12/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v12/config.json
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v12/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v12-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-v12-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v12-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-v12-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v12-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-v12-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v12-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-v12-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.22s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.54s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.94s/it]
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.46it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.46it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.23it/s]
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: Saving duration: 2.183s
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.620s
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v12_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer completed after 94.2s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v12-mkmlizer
Pipeline stage MKMLizer completed in 95.19s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v12
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v12 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v12 ready after 50.26210880279541s
Pipeline stage ISVCDeployer completed in 57.65s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.077504873275757s
Received healthy response to inference request in 1.3011207580566406s
Received healthy response to inference request in 1.284229040145874s
Received healthy response to inference request in 1.247469186782837s
Received healthy response to inference request in 1.2991328239440918s
5 requests
0 failed requests
5th percentile: 1.2548211574554444
10th percentile: 1.2621731281280517
20th percentile: 1.2768770694732665
30th percentile: 1.2872097969055176
40th percentile: 1.2931713104248046
50th percentile: 1.2991328239440918
60th percentile: 1.2999279975891114
70th percentile: 1.300723171234131
80th percentile: 1.456397581100464
90th percentile: 1.7669512271881105
95th percentile: 1.9222280502319335
99th percentile: 2.046449508666992
mean time: 1.44189133644104
Pipeline stage StressChecker completed in 7.92s
chaiml-sao10k-l3-rp-v3-3_v12 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v12 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics