submission_id: chaiml-sao10k-l3-rp-v3-3_v25
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 drama<|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: 2024-07-11T18:50:26+00:00
model_name: chaiml-sao10k-l3-rp-v3-3_v25
model_group: ChaiML/sao10k-l3-rp-v3-3
num_battles: 40649
num_wins: 21010
celo_rating: 1205.26
alignment_score: None
alignment_samples: 0
propriety_score: 0.7198158253751705
propriety_total_count: 5864.0
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_v25
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: 0.5168638834903687
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ Version: 0.8.14 ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: Downloaded to shared memory in 23.307s
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:23, 2.78s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:22, 3.35it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:32, 8.06it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.75it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:10, 22.27it/s] Loading 0: 24%|██▎ | 69/291 [00:06<00:09, 23.53it/s] Loading 0: 29%|██▉ | 85/291 [00:06<00:05, 34.60it/s] Loading 0: 33%|███▎ | 97/291 [00:06<00:04, 43.11it/s] Loading 0: 38%|███▊ | 112/291 [00:06<00:03, 55.44it/s] Loading 0: 43%|████▎ | 124/291 [00:06<00:02, 63.96it/s] Loading 0: 48%|████▊ | 139/291 [00:07<00:01, 78.66it/s] Loading 0: 52%|█████▏ | 152/291 [00:07<00:01, 87.65it/s] Loading 0: 57%|█████▋ | 166/291 [00:07<00:02, 56.32it/s] Loading 0: 61%|██████ | 177/291 [00:07<00:01, 63.79it/s] Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 80.27it/s] Loading 0: 70%|███████ | 205/291 [00:07<00:00, 86.15it/s] Loading 0: 75%|███████▍ | 217/291 [00:07<00:00, 92.56it/s] Loading 0: 79%|███████▉ | 230/291 [00:08<00:00, 98.20it/s] Loading 0: 84%|████████▍ | 245/291 [00:08<00:00, 110.51it/s] Loading 0: 89%|████████▊ | 258/291 [00:08<00:00, 108.62it/s] Loading 0: 93%|█████████▎| 270/291 [00:08<00:00, 59.28it/s] Loading 0: 97%|█████████▋| 283/291 [00:08<00:00, 70.21it/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-v25-mkmlizer: quantized model in 28.791s
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 52.098s
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v25
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v25/config.json
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v25/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v25/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v25/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v25/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: loading reward model from ChaiML/gpt2_medium_pairwise_60m_step_937500
chaiml-sao10k-l3-rp-v3-3-v25-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-v25-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v25-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-v25-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v25-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-v25-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v25-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-v25-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: Saving duration: 0.496s
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: Processed model ChaiML/gpt2_medium_pairwise_60m_step_937500 in 4.082s
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v25_reward
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v25_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v25_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v25_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v25_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v25_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v25_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v25_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer completed after 83.91s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v25-mkmlizer
Pipeline stage MKMLizer completed in 84.86s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v25
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v25 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v25 ready after 50.26229667663574s
Pipeline stage ISVCDeployer completed in 57.61s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9959640502929688s
Received healthy response to inference request in 1.2297265529632568s
Received healthy response to inference request in 1.2051525115966797s
Received healthy response to inference request in 1.186110258102417s
Received healthy response to inference request in 1.208693027496338s
5 requests
0 failed requests
5th percentile: 1.1899187088012695
10th percentile: 1.193727159500122
20th percentile: 1.2013440608978272
30th percentile: 1.2058606147766113
40th percentile: 1.2072768211364746
50th percentile: 1.208693027496338
60th percentile: 1.2171064376831056
70th percentile: 1.225519847869873
80th percentile: 1.3829740524291994
90th percentile: 1.6894690513610842
95th percentile: 1.8427165508270262
99th percentile: 1.9653145503997802
mean time: 1.365129280090332
Pipeline stage StressChecker completed in 7.46s
chaiml-sao10k-l3-rp-v3-3_v25 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v25 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics