sao10k-nemo-rp-v1

developer_uid: sao10k

submission_id: sao10k-nemo-rp-v1_v1

model_name: Nemo-RP-Iteration-1

model_group: Sao10K/Nemo-RP-v1

status: torndown

timestamp: 2024-08-01T09:49:55+00:00

num_battles: 17828

num_wins: 9411

celo_rating: 1229.08

family_friendly_score: 0.0

submission_type: basic

model_repo: Sao10K/Nemo-RP-v1

model_architecture: MistralForCausalLM

reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

display_name: Nemo-RP-Iteration-1

is_internal_developer: False

language_model: Sao10K/Nemo-RP-v1

model_size: 13B

ranking_group: single

us_pacific_date: 2024-08-01

win_ratio: 0.5278774960735921

generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.15, 'top_k': 50, 'presence_penalty': 0.15, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', '\nYou:', '</s>', '<|', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64, 'reward_max_token_input': 512}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}

reward_formatter: {'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True, 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name sao10k-nemo-rp-v1-v1-mkmlizer
Waiting for job on sao10k-nemo-rp-v1-v1-mkmlizer to finish
sao10k-nemo-rp-v1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-nemo-rp-v1-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║       /___/                                                         ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-nemo-rp-v1-v1-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-nemo-rp-v1-v1-mkmlizer: Downloaded to shared memory in 43.881s
sao10k-nemo-rp-v1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4ho1di85, device:0
sao10k-nemo-rp-v1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-nemo-rp-v1-v1-mkmlizer: quantized model in 36.840s
sao10k-nemo-rp-v1-v1-mkmlizer: Processed model Sao10K/Nemo-RP-v1 in 80.722s
sao10k-nemo-rp-v1-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-nemo-rp-v1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-nemo-rp-v1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-nemo-rp-v1-v1
sao10k-nemo-rp-v1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-nemo-rp-v1-v1/special_tokens_map.json
sao10k-nemo-rp-v1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-nemo-rp-v1-v1/config.json
sao10k-nemo-rp-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-nemo-rp-v1-v1/tokenizer_config.json
sao10k-nemo-rp-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-nemo-rp-v1-v1/tokenizer.json
sao10k-nemo-rp-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-nemo-rp-v1-v1/flywheel_model.0.safetensors
sao10k-nemo-rp-v1-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
sao10k-nemo-rp-v1-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:30,  3.08s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:55,  1.21it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:09,  2.71it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:22,  4.22it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:43,  7.85it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:31, 10.75it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:23, 14.09it/s]
Loading 0:  10%|█         | 37/363 [00:07<00:18, 18.07it/s]
Loading 0:  12%|█▏        | 42/363 [00:07<00:16, 19.76it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:11, 26.63it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:10, 29.28it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:13, 23.26it/s]
Loading 0:  18%|█▊        | 64/363 [00:07<00:10, 27.31it/s]
Loading 0:  19%|█▊        | 68/363 [00:08<00:10, 28.94it/s]
Loading 0:  20%|██        | 73/363 [00:08<00:08, 32.84it/s]
Loading 0:  21%|██▏       | 78/363 [00:08<00:09, 30.82it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 38.92it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:06, 40.35it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 42.32it/s]
Loading 0:  28%|██▊       | 100/363 [00:08<00:06, 43.48it/s]
Loading 0:  29%|██▉       | 105/363 [00:08<00:06, 37.04it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:05, 44.67it/s]
Loading 0:  32%|███▏      | 117/363 [00:09<00:05, 42.05it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:05, 42.33it/s]
Loading 0:  35%|███▍      | 127/363 [00:09<00:05, 42.96it/s]
Loading 0:  36%|███▋      | 132/363 [00:09<00:06, 35.12it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:05, 42.93it/s]
Loading 0:  40%|███▉      | 144/363 [00:09<00:05, 42.86it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:04, 43.16it/s]
Loading 0:  43%|████▎     | 155/363 [00:10<00:04, 41.86it/s]
Loading 0:  44%|████▍     | 160/363 [00:10<00:07, 27.42it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:06, 32.24it/s]
Loading 0:  47%|████▋     | 170/363 [00:10<00:05, 32.29it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:05, 34.96it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:05, 34.23it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:04, 38.57it/s]
Loading 0:  53%|█████▎    | 191/363 [00:11<00:04, 39.03it/s]
Loading 0:  54%|█████▍    | 196/363 [00:11<00:04, 38.60it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:03, 43.10it/s]
Loading 0:  57%|█████▋    | 207/363 [00:11<00:03, 42.81it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:03, 43.15it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 42.52it/s]
Loading 0:  61%|██████▏   | 223/363 [00:11<00:03, 41.47it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:02, 45.56it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:02, 43.57it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:02, 43.25it/s]
Loading 0:  67%|██████▋   | 244/363 [00:12<00:02, 44.89it/s]
Loading 0:  69%|██████▊   | 249/363 [00:12<00:03, 36.09it/s]
Loading 0:  71%|███████   | 256/363 [00:12<00:03, 29.57it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:03, 30.63it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:02, 35.06it/s]
Loading 0:  75%|███████▍  | 272/363 [00:13<00:02, 36.90it/s]
Loading 0:  76%|███████▌  | 276/363 [00:13<00:02, 35.67it/s]
Loading 0:  78%|███████▊  | 284/363 [00:13<00:01, 43.69it/s]
Loading 0:  80%|███████▉  | 289/363 [00:13<00:01, 44.97it/s]
Loading 0:  81%|████████  | 294/363 [00:13<00:01, 38.44it/s]
Loading 0:  83%|████████▎ | 301/363 [00:13<00:01, 45.41it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:01, 44.54it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:01, 43.48it/s]
Loading 0:  87%|████████▋ | 316/363 [00:14<00:01, 44.19it/s]
Loading 0:  88%|████████▊ | 321/363 [00:14<00:01, 37.11it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:00, 44.14it/s]
Loading 0:  92%|█████████▏| 333/363 [00:14<00:00, 43.22it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 43.29it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 42.06it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 41.26it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 29.68it/s]
Loading 0:  99%|█████████▉| 359/363 [00:15<00:00, 30.65it/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-nemo-rp-v1-v1-mkmlizer:   warnings.warn(
sao10k-nemo-rp-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-nemo-rp-v1-v1-mkmlizer:   warnings.warn(
sao10k-nemo-rp-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-nemo-rp-v1-v1-mkmlizer:   warnings.warn(
sao10k-nemo-rp-v1-v1-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.42s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  3.99s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.20s/it]
sao10k-nemo-rp-v1-v1-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.33it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.83it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.49it/s]
sao10k-nemo-rp-v1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-nemo-rp-v1-v1-mkmlizer: Saving duration: 1.370s
sao10k-nemo-rp-v1-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.274s
sao10k-nemo-rp-v1-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-nemo-rp-v1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-nemo-rp-v1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-nemo-rp-v1-v1_reward
sao10k-nemo-rp-v1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-nemo-rp-v1-v1_reward/config.json
sao10k-nemo-rp-v1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-nemo-rp-v1-v1_reward/special_tokens_map.json
sao10k-nemo-rp-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-nemo-rp-v1-v1_reward/tokenizer_config.json
sao10k-nemo-rp-v1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-nemo-rp-v1-v1_reward/merges.txt
sao10k-nemo-rp-v1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-nemo-rp-v1-v1_reward/vocab.json
sao10k-nemo-rp-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-nemo-rp-v1-v1_reward/tokenizer.json
sao10k-nemo-rp-v1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-nemo-rp-v1-v1_reward/reward.tensors
Job sao10k-nemo-rp-v1-v1-mkmlizer completed after 128.91s with status: succeeded
Stopping job with name sao10k-nemo-rp-v1-v1-mkmlizer
Pipeline stage MKMLizer completed in 129.96s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-nemo-rp-v1-v1
Waiting for inference service sao10k-nemo-rp-v1-v1 to be ready
Inference service sao10k-nemo-rp-v1-v1 ready after 120.99895429611206s
Pipeline stage ISVCDeployer completed in 122.85s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5422616004943848s
Received healthy response to inference request in 1.7394511699676514s
Received healthy response to inference request in 1.7483813762664795s
Received healthy response to inference request in 2.319875478744507s
Received healthy response to inference request in 1.3339378833770752s
5 requests
0 failed requests
5th percentile: 1.4150405406951905
10th percentile: 1.4961431980133058
20th percentile: 1.658348512649536
30th percentile: 1.741237211227417
40th percentile: 1.7448092937469482
50th percentile: 1.7483813762664795
60th percentile: 1.9769790172576904
70th percentile: 2.2055766582489014
80th percentile: 2.3643527030944824
90th percentile: 2.4533071517944336
95th percentile: 2.497784376144409
99th percentile: 2.53336615562439
mean time: 1.9367815017700196
Pipeline stage StressChecker completed in 10.41s
sao10k-nemo-rp-v1_v1 status is now deployed due to DeploymentManager action
sao10k-nemo-rp-v1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-nemo-rp-v1_v1
Running pipeline stage ISVCDeleter
Checking if service sao10k-nemo-rp-v1-v1 is running
Tearing down inference service sao10k-nemo-rp-v1-v1
Service sao10k-nemo-rp-v1-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.54s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-nemo-rp-v1-v1/config.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-nemo-rp-v1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.92s
sao10k-nemo-rp-v1_v1 status is now torndown due to DeploymentManager action