submission_id: chaiml-sao10k-l3-rp-v3-3_v27
developer_uid: dzhao1
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|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-07-11T22:15:10+00:00
model_name: chaiml-sao10k-l3-rp-v3-3_v27
model_group: ChaiML/sao10k-l3-rp-v3-3
num_battles: 32582
num_wins: 17925
celo_rating: 1232.24
alignment_score: None
alignment_samples: 0
propriety_score: 0.7078089461713419
propriety_total_count: 6595.0
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_v27
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: 0.5501503897857712
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ Version: 0.8.14 ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: Downloaded to shared memory in 37.348s
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-sao10k-l3-rp-v3-3_v16: ('http://chaiml-sao10k-l3-rp-v3-3-v16-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:38608->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:59, 2.91s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:26, 3.20it/s] Loading 0: 10%|▉ | 28/291 [00:06<00:34, 7.71it/s] Loading 0: 14%|█▍ | 41/291 [00:06<00:19, 13.13it/s] Loading 0: 19%|█▉ | 55/291 [00:06<00:11, 20.67it/s] Loading 0: 23%|██▎ | 67/291 [00:06<00:10, 21.56it/s] Loading 0: 27%|██▋ | 78/291 [00:06<00:07, 28.25it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:04, 41.08it/s] Loading 0: 36%|███▌ | 105/291 [00:07<00:03, 48.64it/s] Loading 0: 42%|████▏ | 121/291 [00:07<00:02, 63.69it/s] Loading 0: 46%|████▌ | 133/291 [00:07<00:02, 71.71it/s] Loading 0: 51%|█████ | 148/291 [00:07<00:01, 84.90it/s] Loading 0: 55%|█████▍ | 160/291 [00:07<00:01, 90.05it/s] Loading 0: 59%|█████▉ | 172/291 [00:08<00:02, 51.70it/s] Loading 0: 64%|██████▎ | 185/291 [00:08<00:01, 61.61it/s] Loading 0: 68%|██████▊ | 198/291 [00:08<00:01, 72.66it/s] Loading 0: 73%|███████▎ | 211/291 [00:08<00:00, 83.82it/s] Loading 0: 77%|███████▋ | 223/291 [00:08<00:00, 89.86it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 102.84it/s] Loading 0: 86%|████████▋ | 251/291 [00:08<00:00, 104.95it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 111.95it/s] Loading 0: 96%|█████████▌| 278/291 [00:09<00:00, 52.70it/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-v27-mkmlizer: quantized model in 31.029s
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 68.377s
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v27
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v27/config.json
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v27/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v27/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v27/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v27/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v27-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-v27-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v27-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-v27-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v27-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-v27-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v27-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-v27-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.08s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.18s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.62s/it]
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.34it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.32it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.09it/s]
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: Saving duration: 2.410s
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.999s
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v27_reward
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v27_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v27_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v27_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v27_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v27_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v27_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v27_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer completed after 131.92s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v27-mkmlizer
Pipeline stage MKMLizer completed in 132.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v27
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v27 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v27 ready after 50.26074433326721s
Pipeline stage ISVCDeployer completed in 57.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.012230634689331s
Received healthy response to inference request in 1.3303794860839844s
Received healthy response to inference request in 1.3620433807373047s
Received healthy response to inference request in 1.3733346462249756s
Received healthy response to inference request in 1.3518242835998535s
5 requests
0 failed requests
5th percentile: 1.3346684455871582
10th percentile: 1.3389574050903321
20th percentile: 1.3475353240966796
30th percentile: 1.3538681030273438
40th percentile: 1.3579557418823243
50th percentile: 1.3620433807373047
60th percentile: 1.366559886932373
70th percentile: 1.3710763931274415
80th percentile: 1.5011138439178469
90th percentile: 1.756672239303589
95th percentile: 1.8844514369964598
99th percentile: 1.9866747951507568
mean time: 1.48596248626709
Pipeline stage StressChecker completed in 8.20s
chaiml-sao10k-l3-rp-v3-3_v27 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v27 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics