submission_id: sao10k-l3-mitama-3-1_v1
developer_uid: sao10k
best_of: 16
celo_rating: 1216.62
display_name: Miitama1
family_friendly_score: 0.0
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-Mitama-3.1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Sao10K/L3-Mitama-3.1
model_name: Miitama1
model_num_parameters: 8030261248.0
model_repo: Sao10K/L3-Mitama-3.1
model_size: 8B
num_battles: 13135
num_wins: 6456
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: 2024-08-03T08:49:33+00:00
us_pacific_date: 2024-08-03
win_ratio: 0.4915112295393986
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-mitama-3-1-v1-mkmlizer
Waiting for job on sao10k-l3-mitama-3-1-v1-mkmlizer to finish
sao10k-l3-mitama-3-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-mitama-3-1-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║       /___/                                                         ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║  Version: 0.9.9                                                     ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-mitama-3-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-mitama-3-1-v1-mkmlizer: Downloaded to shared memory in 28.672s
sao10k-l3-mitama-3-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpiwz0uvyi, device:0
sao10k-l3-mitama-3-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-mitama-3-1-v1-mkmlizer: quantized model in 26.185s
sao10k-l3-mitama-3-1-v1-mkmlizer: Processed model Sao10K/L3-Mitama-3.1 in 54.857s
sao10k-l3-mitama-3-1-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-mitama-3-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-mitama-3-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-mitama-3-1-v1
sao10k-l3-mitama-3-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-mitama-3-1-v1/config.json
sao10k-l3-mitama-3-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-mitama-3-1-v1/special_tokens_map.json
sao10k-l3-mitama-3-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-mitama-3-1-v1/tokenizer_config.json
sao10k-l3-mitama-3-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-mitama-3-1-v1/tokenizer.json
sao10k-l3-mitama-3-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-mitama-3-1-v1/flywheel_model.0.safetensors
sao10k-l3-mitama-3-1-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
sao10k-l3-mitama-3-1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:35,  2.41s/it]
Loading 0:   2%|▏         | 6/291 [00:04<03:04,  1.54it/s]
Loading 0:   4%|▍         | 13/291 [00:05<01:05,  4.22it/s]
Loading 0:   7%|▋         | 20/291 [00:05<00:36,  7.49it/s]
Loading 0:   9%|▊         | 25/291 [00:05<00:25, 10.37it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:16, 15.60it/s]
Loading 0:  14%|█▍        | 42/291 [00:05<00:11, 21.93it/s]
Loading 0:  17%|█▋        | 50/291 [00:05<00:08, 29.15it/s]
Loading 0:  19%|█▉        | 56/291 [00:05<00:07, 31.91it/s]
Loading 0:  21%|██▏       | 62/291 [00:05<00:06, 36.04it/s]
Loading 0:  23%|██▎       | 68/291 [00:06<00:05, 39.36it/s]
Loading 0:  25%|██▌       | 74/291 [00:06<00:05, 38.84it/s]
Loading 0:  27%|██▋       | 79/291 [00:06<00:05, 40.18it/s]
Loading 0:  29%|██▉       | 84/291 [00:06<00:06, 31.17it/s]
Loading 0:  30%|███       | 88/291 [00:06<00:06, 31.73it/s]
Loading 0:  33%|███▎      | 96/291 [00:06<00:05, 35.59it/s]
Loading 0:  36%|███▌      | 104/291 [00:07<00:04, 43.02it/s]
Loading 0:  37%|███▋      | 109/291 [00:07<00:04, 44.49it/s]
Loading 0:  39%|███▉      | 114/291 [00:07<00:04, 38.07it/s]
Loading 0:  42%|████▏     | 122/291 [00:07<00:03, 45.84it/s]
Loading 0:  44%|████▍     | 128/291 [00:07<00:03, 45.50it/s]
Loading 0:  46%|████▌     | 133/291 [00:07<00:03, 45.68it/s]
Loading 0:  48%|████▊     | 140/291 [00:07<00:02, 51.07it/s]
Loading 0:  50%|█████     | 146/291 [00:07<00:03, 47.13it/s]
Loading 0:  52%|█████▏    | 151/291 [00:08<00:03, 45.65it/s]
Loading 0:  54%|█████▍    | 157/291 [00:08<00:02, 49.22it/s]
Loading 0:  56%|█████▌    | 163/291 [00:08<00:02, 51.03it/s]
Loading 0:  58%|█████▊    | 169/291 [00:08<00:02, 45.09it/s]
Loading 0:  61%|██████    | 177/291 [00:08<00:02, 45.68it/s]
Loading 0:  64%|██████▎   | 185/291 [00:08<00:02, 52.76it/s]
Loading 0:  66%|██████▌   | 191/291 [00:08<00:02, 49.68it/s]
Loading 0:  68%|██████▊   | 197/291 [00:08<00:01, 50.14it/s]
Loading 0:  70%|███████   | 204/291 [00:09<00:02, 33.74it/s]
Loading 0:  73%|███████▎  | 211/291 [00:09<00:02, 39.52it/s]
Loading 0:  74%|███████▍  | 216/291 [00:09<00:01, 40.33it/s]
Loading 0:  76%|███████▋  | 222/291 [00:09<00:01, 38.38it/s]
Loading 0:  79%|███████▉  | 230/291 [00:09<00:01, 46.92it/s]
Loading 0:  81%|████████  | 236/291 [00:09<00:01, 45.94it/s]
Loading 0:  83%|████████▎ | 242/291 [00:10<00:01, 46.46it/s]
Loading 0:  85%|████████▌ | 248/291 [00:10<00:00, 49.38it/s]
Loading 0:  87%|████████▋ | 254/291 [00:10<00:00, 47.28it/s]
Loading 0:  89%|████████▉ | 259/291 [00:10<00:00, 46.26it/s]
Loading 0:  91%|█████████▏| 266/291 [00:10<00:00, 50.16it/s]
Loading 0:  93%|█████████▎| 272/291 [00:10<00:00, 47.55it/s]
Loading 0:  95%|█████████▌| 277/291 [00:10<00:00, 46.71it/s]
Loading 0:  98%|█████████▊| 284/291 [00:10<00:00, 50.96it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 47.25it/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-mitama-3-1-v1-mkmlizer:   warnings.warn(
sao10k-l3-mitama-3-1-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-mitama-3-1-v1-mkmlizer:   warnings.warn(
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
sao10k-l3-mitama-3-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-mitama-3-1-v1-mkmlizer: Saving duration: 1.400s
sao10k-l3-mitama-3-1-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.889s
sao10k-l3-mitama-3-1-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-mitama-3-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-mitama-3-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-mitama-3-1-v1_reward
sao10k-l3-mitama-3-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-mitama-3-1-v1_reward/merges.txt
sao10k-l3-mitama-3-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-mitama-3-1-v1_reward/vocab.json
sao10k-l3-mitama-3-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-mitama-3-1-v1_reward/tokenizer.json
sao10k-l3-mitama-3-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-mitama-3-1-v1_reward/reward.tensors
Job sao10k-l3-mitama-3-1-v1-mkmlizer completed after 105.91s with status: succeeded
Stopping job with name sao10k-l3-mitama-3-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-mitama-3-1-v1
Waiting for inference service sao10k-l3-mitama-3-1-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service sao10k-l3-mitama-3-1-v1 ready after 151.54124808311462s
Pipeline stage ISVCDeployer completed in 152.92s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3377673625946045s
Received healthy response to inference request in 1.4974660873413086s
Received healthy response to inference request in 1.444892406463623s
Received healthy response to inference request in 1.4207403659820557s
Received healthy response to inference request in 1.4817802906036377s
5 requests
0 failed requests
5th percentile: 1.4255707740783692
10th percentile: 1.4304011821746827
20th percentile: 1.4400619983673095
30th percentile: 1.452269983291626
40th percentile: 1.467025136947632
50th percentile: 1.4817802906036377
60th percentile: 1.4880546092987061
70th percentile: 1.4943289279937744
80th percentile: 1.665526342391968
90th percentile: 2.001646852493286
95th percentile: 2.169707107543945
99th percentile: 2.3041553115844726
mean time: 1.636529302597046
Pipeline stage StressChecker completed in 8.84s
sao10k-l3-mitama-3-1_v1 status is now deployed due to DeploymentManager action
sao10k-l3-mitama-3-1_v1 status is now inactive due to auto deactivation removed underperforming models
sao10k-l3-mitama-3-1_v1 status is now torndown due to DeploymentManager action