submission_id: sao10k-l3-1-8b-stheno-3-_9545_v1
developer_uid: sao10k
alignment_samples: 0
best_of: 16
celo_rating: 1222.89
display_name: stheno2
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}
generation_params: {'temperature': 1.2, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}', 'You:', '\n\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: Sao10K/L3.1-8B-Stheno-3.4-Beta-2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Sao10K/L3.1-8B-Stheno-3.
model_name: stheno2
model_num_parameters: 8030261248.0
model_repo: Sao10K/L3.1-8B-Stheno-3.4-Beta-2
model_size: 8B
num_battles: 11069
num_wins: 5725
propriety_score: 0.7073863636363636
propriety_total_count: 1056.0
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-05T15:00:42+00:00
us_pacific_date: 2024-08-05
win_ratio: 0.5172102267594182
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer
Waiting for job on sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer to finish
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ _____ __ __ ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ /___/ ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ Version: 0.9.9 ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ belonging to: ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ║ ║
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_goner_2024-08-03: ('http://mistralai-mixtral-8x7b-3473-v106-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:50428->127.0.0.1:8080: read: connection reset by peer\n')
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: Downloaded to shared memory in 32.682s
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf2xcvf85, device:0
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: quantized model in 25.943s
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: Processed model Sao10K/L3.1-8B-Stheno-3.4-Beta-2 in 58.625s
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-1-8b-stheno-3-9545-v1
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-1-8b-stheno-3-9545-v1/config.json
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-1-8b-stheno-3-9545-v1/special_tokens_map.json
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-1-8b-stheno-3-9545-v1/tokenizer_config.json
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-1-8b-stheno-3-9545-v1/tokenizer.json
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-1-8b-stheno-3-9545-v1/flywheel_model.0.safetensors
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 50.54it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:03, 70.02it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 69.45it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 75.79it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 88.49it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 86.97it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 87.80it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:02, 86.06it/s] Loading 0: 30%|███ | 88/291 [00:02<00:08, 23.08it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 33.54it/s] Loading 0: 40%|███▉ | 115/291 [00:02<00:04, 40.70it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 46.84it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:02, 53.61it/s] Loading 0: 49%|████▉ | 143/291 [00:02<00:02, 61.91it/s] Loading 0: 52%|█████▏ | 152/291 [00:02<00:02, 64.33it/s] Loading 0: 55%|█████▌ | 161/291 [00:02<00:01, 65.11it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 74.96it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 25.10it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 34.84it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 42.21it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 48.10it/s] Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 53.47it/s] Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 59.36it/s] Loading 0: 86%|████████▌ | 250/291 [00:04<00:00, 65.20it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 70.18it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 73.14it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 74.38it/s] Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 72.26it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: warnings.warn(
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: warnings.warn(
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: Saving duration: 1.391s
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.155s
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-1-8b-stheno-3-9545-v1_reward
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-1-8b-stheno-3-9545-v1_reward/merges.txt
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-1-8b-stheno-3-9545-v1_reward/vocab.json
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-1-8b-stheno-3-9545-v1_reward/tokenizer.json
sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-1-8b-stheno-3-9545-v1_reward/reward.tensors
Job sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer completed after 104.57s with status: succeeded
Stopping job with name sao10k-l3-1-8b-stheno-3-9545-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-1-8b-stheno-3-9545-v1
Waiting for inference service sao10k-l3-1-8b-stheno-3-9545-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service sao10k-l3-1-8b-stheno-3-9545-v1 ready after 161.0123689174652s
Pipeline stage ISVCDeployer completed in 163.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1553897857666016s
Received healthy response to inference request in 1.4449880123138428s
Received healthy response to inference request in 1.2520389556884766s
Received healthy response to inference request in 1.3535301685333252s
Received healthy response to inference request in 1.2552402019500732s
5 requests
0 failed requests
5th percentile: 1.252679204940796
10th percentile: 1.2533194541931152
20th percentile: 1.2545999526977538
30th percentile: 1.2748981952667235
40th percentile: 1.3142141819000244
50th percentile: 1.3535301685333252
60th percentile: 1.3901133060455322
70th percentile: 1.4266964435577392
80th percentile: 1.5870683670043946
90th percentile: 1.8712290763854982
95th percentile: 2.0133094310760495
99th percentile: 2.126973714828491
mean time: 1.492237424850464
Pipeline stage StressChecker completed in 8.25s
sao10k-l3-1-8b-stheno-3-_9545_v1 status is now deployed due to DeploymentManager action
sao10k-l3-1-8b-stheno-3-_9545_v1 status is now inactive due to auto deactivation removed underperforming models
sao10k-l3-1-8b-stheno-3-_9545_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics