sao10k-l3-8b-niitama-v1

submission_id: sao10k-l3-8b-niitama-v1_v1

developer_uid: sao10k

best_of: 16

celo_rating: 1249.01

display_name: RP-v5-Expr2

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': 1.4, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}

is_internal_developer: False

language_model: Sao10K/L3-8B-Niitama-v1

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Sao10K/L3-8B-Niitama-v1

model_name: RP-v5-Expr2

model_num_parameters: 8030261248.0

model_repo: Sao10K/L3-8B-Niitama-v1

model_size: 8B

num_battles: 12156

num_wins: 6837

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: 2024-07-26T21:09:35+00:00

us_pacific_date: 2024-07-26

win_ratio: 0.5624383020730503

Download Preference Data

Resubmit model

Running pipeline stage MKMLizer
Starting job with name sao10k-l3-8b-niitama-v1-v1-mkmlizer
Waiting for job on sao10k-l3-8b-niitama-v1-v1-mkmlizer to finish
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║       /___/                                                         ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-8b-niitama-v1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-8b-niitama-v1-v1-mkmlizer: Downloaded to shared memory in 26.447s
sao10k-l3-8b-niitama-v1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3lst0w2m, device:0
sao10k-l3-8b-niitama-v1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-8b-niitama-v1-v1-mkmlizer: quantized model in 25.533s
sao10k-l3-8b-niitama-v1-v1-mkmlizer: Processed model Sao10K/L3-8B-Niitama-v1 in 51.980s
sao10k-l3-8b-niitama-v1-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-8b-niitama-v1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-8b-niitama-v1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-8b-niitama-v1-v1
sao10k-l3-8b-niitama-v1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-8b-niitama-v1-v1/config.json
sao10k-l3-8b-niitama-v1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-8b-niitama-v1-v1/special_tokens_map.json
sao10k-l3-8b-niitama-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-8b-niitama-v1-v1/tokenizer_config.json
sao10k-l3-8b-niitama-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-8b-niitama-v1-v1/tokenizer.json
sao10k-l3-8b-niitama-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-8b-niitama-v1-v1/flywheel_model.0.safetensors
sao10k-l3-8b-niitama-v1-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
sao10k-l3-8b-niitama-v1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:28,  2.38s/it]
Loading 0:   2%|▏         | 6/291 [00:04<03:03,  1.55it/s]
Loading 0:   4%|▍         | 13/291 [00:05<01:05,  4.25it/s]
Loading 0:   7%|▋         | 20/291 [00:05<00:35,  7.61it/s]
Loading 0:   9%|▊         | 25/291 [00:05<00:25, 10.56it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:16, 16.00it/s]
Loading 0:  14%|█▍        | 42/291 [00:05<00:11, 22.56it/s]
Loading 0:  17%|█▋        | 50/291 [00:05<00:08, 29.80it/s]
Loading 0:  19%|█▉        | 56/291 [00:05<00:07, 32.29it/s]
Loading 0:  21%|██▏       | 62/291 [00:06<00:08, 27.58it/s]
Loading 0:  24%|██▎       | 69/291 [00:06<00:07, 31.48it/s]
Loading 0:  27%|██▋       | 78/291 [00:06<00:05, 37.70it/s]
Loading 0:  30%|██▉       | 86/291 [00:06<00:04, 45.26it/s]
Loading 0:  32%|███▏      | 92/291 [00:06<00:04, 45.56it/s]
Loading 0:  34%|███▎      | 98/291 [00:06<00:04, 47.30it/s]
Loading 0:  36%|███▌      | 105/291 [00:06<00:03, 46.52it/s]
Loading 0:  39%|███▉      | 113/291 [00:07<00:03, 53.46it/s]
Loading 0:  41%|████      | 119/291 [00:07<00:03, 49.74it/s]
Loading 0:  43%|████▎     | 125/291 [00:07<00:03, 50.16it/s]
Loading 0:  45%|████▌     | 132/291 [00:07<00:03, 47.53it/s]
Loading 0:  48%|████▊     | 140/291 [00:07<00:02, 54.39it/s]
Loading 0:  50%|█████     | 146/291 [00:07<00:02, 49.80it/s]
Loading 0:  52%|█████▏    | 152/291 [00:07<00:02, 50.86it/s]
Loading 0:  54%|█████▍    | 158/291 [00:07<00:02, 52.89it/s]
Loading 0:  56%|█████▋    | 164/291 [00:08<00:02, 51.27it/s]
Loading 0:  58%|█████▊    | 170/291 [00:08<00:03, 35.76it/s]
Loading 0:  60%|██████    | 176/291 [00:08<00:02, 40.20it/s]
Loading 0:  63%|██████▎   | 182/291 [00:08<00:02, 40.94it/s]
Loading 0:  64%|██████▍   | 187/291 [00:08<00:02, 42.71it/s]
Loading 0:  67%|██████▋   | 194/291 [00:08<00:01, 49.27it/s]
Loading 0:  69%|██████▊   | 200/291 [00:08<00:01, 48.56it/s]
Loading 0:  71%|███████   | 206/291 [00:09<00:01, 51.21it/s]
Loading 0:  73%|███████▎  | 213/291 [00:09<00:01, 47.70it/s]
Loading 0:  76%|███████▋  | 222/291 [00:09<00:01, 49.44it/s]
Loading 0:  79%|███████▉  | 231/291 [00:09<00:01, 51.59it/s]
Loading 0:  82%|████████▏ | 239/291 [00:09<00:00, 57.60it/s]
Loading 0:  85%|████████▍ | 246/291 [00:09<00:00, 53.91it/s]
Loading 0:  87%|████████▋ | 252/291 [00:09<00:00, 53.46it/s]
Loading 0:  89%|████████▊ | 258/291 [00:10<00:00, 49.71it/s]
Loading 0:  91%|█████████▏| 266/291 [00:10<00:00, 40.59it/s]
Loading 0:  93%|█████████▎| 272/291 [00:10<00:00, 41.72it/s]
Loading 0:  96%|█████████▌| 278/291 [00:10<00:00, 45.45it/s]
Loading 0:  98%|█████████▊| 284/291 [00:10<00:00, 48.64it/s]
Loading 0: 100%|█████████▉| 290/291 [00:10<00:00, 49.01it/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-l3-8b-niitama-v1-v1-mkmlizer:   warnings.warn(
sao10k-l3-8b-niitama-v1-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-l3-8b-niitama-v1-v1-mkmlizer:   warnings.warn(
sao10k-l3-8b-niitama-v1-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-l3-8b-niitama-v1-v1-mkmlizer:   warnings.warn(
sao10k-l3-8b-niitama-v1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-8b-niitama-v1-v1-mkmlizer: Saving duration: 1.416s
sao10k-l3-8b-niitama-v1-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.885s
sao10k-l3-8b-niitama-v1-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-8b-niitama-v1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-8b-niitama-v1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-8b-niitama-v1-v1_reward
sao10k-l3-8b-niitama-v1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-8b-niitama-v1-v1_reward/config.json
sao10k-l3-8b-niitama-v1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-8b-niitama-v1-v1_reward/special_tokens_map.json
sao10k-l3-8b-niitama-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-8b-niitama-v1-v1_reward/tokenizer_config.json
sao10k-l3-8b-niitama-v1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-8b-niitama-v1-v1_reward/merges.txt
sao10k-l3-8b-niitama-v1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-8b-niitama-v1-v1_reward/vocab.json
sao10k-l3-8b-niitama-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-8b-niitama-v1-v1_reward/tokenizer.json
sao10k-l3-8b-niitama-v1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-8b-niitama-v1-v1_reward/reward.tensors
Job sao10k-l3-8b-niitama-v1-v1-mkmlizer completed after 95.93s with status: succeeded
Stopping job with name sao10k-l3-8b-niitama-v1-v1-mkmlizer
Pipeline stage MKMLizer completed in 97.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-8b-niitama-v1-v1
Waiting for inference service sao10k-l3-8b-niitama-v1-v1 to be ready
Inference service sao10k-l3-8b-niitama-v1-v1 ready after 80.8804247379303s
Pipeline stage ISVCDeployer completed in 82.65s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.316753625869751s
Received healthy response to inference request in 1.4640684127807617s
Received healthy response to inference request in 1.431875228881836s
Received healthy response to inference request in 1.4533436298370361s
Received healthy response to inference request in 1.4766151905059814s
5 requests
0 failed requests
5th percentile: 1.436168909072876
10th percentile: 1.440462589263916
20th percentile: 1.449049949645996
30th percentile: 1.4554885864257812
40th percentile: 1.4597784996032714
50th percentile: 1.4640684127807617
60th percentile: 1.4690871238708496
70th percentile: 1.4741058349609375
80th percentile: 1.6446428775787356
90th percentile: 1.9806982517242433
95th percentile: 2.148725938796997
99th percentile: 2.2831480884552002
mean time: 1.6285312175750732
Pipeline stage StressChecker completed in 8.91s
sao10k-l3-8b-niitama-v1_v1 status is now deployed due to DeploymentManager action
sao10k-l3-8b-niitama-v1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-8b-niitama-v1_v1
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-8b-niitama-v1-v1 is running
Tearing down inference service sao10k-l3-8b-niitama-v1-v1
Service sao10k-l3-8b-niitama-v1-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.86s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-8b-niitama-v1-v1/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-niitama-v1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-niitama-v1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-niitama-v1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-niitama-v1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-8b-niitama-v1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-niitama-v1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-niitama-v1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-niitama-v1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-niitama-v1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-niitama-v1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-niitama-v1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.62s
sao10k-l3-8b-niitama-v1_v1 status is now torndown due to DeploymentManager action