submission_id: chaiml-sao10k-l3-rp-v3-3_v18
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 seriously<|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: 2024-07-11T17:37:55+00:00
model_name: chaiml-sao10k-l3-rp-v3-3_v18
model_group: ChaiML/sao10k-l3-rp-v3-3
num_battles: 39921
num_wins: 20817
celo_rating: 1207.85
alignment_score: None
alignment_samples: 0
propriety_score: 0.7260562034027911
propriety_total_count: 5231.0
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_v18
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: 0.5214548733749155
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ Version: 0.8.14 ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v18-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
Connection pool is full, discarding connection: %s
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: Downloaded to shared memory in 27.308s
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:17, 2.76s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:22, 3.37it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:32, 8.11it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.83it/s] Loading 0: 19%|█▉ | 55/291 [00:05<00:10, 21.77it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:09, 22.79it/s] Loading 0: 26%|██▋ | 77/291 [00:06<00:07, 28.76it/s] Loading 0: 31%|███ | 90/291 [00:06<00:05, 39.18it/s] Loading 0: 35%|███▌ | 103/291 [00:06<00:03, 50.22it/s] Loading 0: 39%|███▉ | 114/291 [00:06<00:03, 58.12it/s] Loading 0: 45%|████▍ | 130/291 [00:06<00:02, 75.24it/s] Loading 0: 49%|████▉ | 142/291 [00:07<00:01, 82.45it/s] Loading 0: 54%|█████▍ | 157/291 [00:07<00:01, 95.44it/s] Loading 0: 58%|█████▊ | 170/291 [00:07<00:02, 54.75it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 67.02it/s] Loading 0: 67%|██████▋ | 195/291 [00:07<00:01, 73.67it/s] Loading 0: 73%|███████▎ | 211/291 [00:07<00:00, 90.48it/s] Loading 0: 77%|███████▋ | 224/291 [00:08<00:00, 97.44it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 107.27it/s] Loading 0: 86%|████████▋ | 251/291 [00:08<00:00, 109.86it/s] Loading 0: 91%|█████████▏| 266/291 [00:08<00:00, 61.46it/s] Loading 0: 96%|█████████▌| 280/291 [00:08<00:00, 73.62it/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-v18-mkmlizer: quantized model in 28.917s
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 56.225s
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v18
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v18/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v18/config.json
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v18/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v18/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v18/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v18-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-v18-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.59s/it] Downloading shards: 100%|██████████| 2/2 [00:11<00:00, 5.78s/it] Downloading shards: 100%|██████████| 2/2 [00:11<00:00, 5.90s/it]
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.67it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.72it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.48it/s]
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: Saving duration: 2.136s
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 16.113s
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v18_reward
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v18_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v18_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v18_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v18_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v18_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v18_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v18_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer completed after 103.93s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v18-mkmlizer
Pipeline stage MKMLizer completed in 104.81s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v18
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v18 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v18 ready after 50.37466740608215s
Pipeline stage ISVCDeployer completed in 57.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.008867025375366s
Received healthy response to inference request in 1.2959914207458496s
Received healthy response to inference request in 1.285538673400879s
Received healthy response to inference request in 1.2726244926452637s
Received healthy response to inference request in 1.2930386066436768s
5 requests
0 failed requests
5th percentile: 1.2752073287963868
10th percentile: 1.2777901649475099
20th percentile: 1.2829558372497558
30th percentile: 1.2870386600494386
40th percentile: 1.2900386333465577
50th percentile: 1.2930386066436768
60th percentile: 1.294219732284546
70th percentile: 1.295400857925415
80th percentile: 1.438566541671753
90th percentile: 1.7237167835235596
95th percentile: 1.8662919044494628
99th percentile: 1.9803520011901856
mean time: 1.4312120437622071
Pipeline stage StressChecker completed in 7.83s
chaiml-sao10k-l3-rp-v3-3_v18 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v18 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics