sao10k-nemo-rp-v5

submission_id: sao10k-nemo-rp-v5_v1

developer_uid: sao10k

best_of: 8

celo_rating: 1227.4

display_name: Nemo-RP-Iteration-5

family_friendly_score: 0.0

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}

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}

is_internal_developer: False

language_model: Sao10K/Nemo-RP-v5

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: Sao10K/Nemo-RP-v5

model_name: Nemo-RP-Iteration-5

model_num_parameters: 12772070400.0

model_repo: Sao10K/Nemo-RP-v5

model_size: 13B

num_battles: 19329

num_wins: 10154

ranking_group: single

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'}

reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634

status: torndown

submission_type: basic

timestamp: 2024-08-01T09:51:18+00:00

us_pacific_date: 2024-08-01

win_ratio: 0.5253246417300429

Resubmit model

Running pipeline stage MKMLizer
Starting job with name sao10k-nemo-rp-v5-v1-mkmlizer
Waiting for job on sao10k-nemo-rp-v5-v1-mkmlizer to finish
sao10k-nemo-rp-v5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-nemo-rp-v5-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║       /___/                                                         ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-nemo-rp-v5-v1-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-nemo-rp-v5-v1-mkmlizer: Downloaded to shared memory in 43.245s
sao10k-nemo-rp-v5-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6na4ow41, device:0
sao10k-nemo-rp-v5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-nemo-rp-v5-v1-mkmlizer: quantized model in 36.556s
sao10k-nemo-rp-v5-v1-mkmlizer: Processed model Sao10K/Nemo-RP-v5 in 79.802s
sao10k-nemo-rp-v5-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-nemo-rp-v5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-nemo-rp-v5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-nemo-rp-v5-v1
sao10k-nemo-rp-v5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-nemo-rp-v5-v1/config.json
sao10k-nemo-rp-v5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-nemo-rp-v5-v1/special_tokens_map.json
sao10k-nemo-rp-v5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-nemo-rp-v5-v1/tokenizer.json
sao10k-nemo-rp-v5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-nemo-rp-v5-v1/flywheel_model.0.safetensors
sao10k-nemo-rp-v5-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
sao10k-nemo-rp-v5-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:16,  3.04s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:51,  1.22it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:08,  2.75it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:21,  4.28it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:40,  8.49it/s]
Loading 0:   8%|▊         | 28/363 [00:06<00:29, 11.54it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:23, 13.81it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:16, 19.92it/s]
Loading 0:  12%|█▏        | 45/363 [00:07<00:13, 23.32it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:11, 26.65it/s]
Loading 0:  15%|█▌        | 55/363 [00:07<00:10, 30.35it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:14, 21.29it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:10, 29.29it/s]
Loading 0:  20%|██        | 73/363 [00:07<00:08, 32.65it/s]
Loading 0:  21%|██▏       | 78/363 [00:08<00:09, 31.44it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 39.79it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:06, 39.74it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:06, 39.68it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:05, 44.18it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:05, 43.38it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 43.14it/s]
Loading 0:  33%|███▎      | 118/363 [00:09<00:05, 43.99it/s]
Loading 0:  34%|███▍      | 123/363 [00:09<00:06, 36.06it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:05, 42.21it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:05, 41.75it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 41.08it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:05, 42.54it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:05, 35.59it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:06, 30.59it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:06, 31.43it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:05, 35.83it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 38.93it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:05, 34.91it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 41.51it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:04, 40.98it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:04, 41.35it/s]
Loading 0:  55%|█████▍    | 199/363 [00:11<00:03, 42.95it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:04, 35.09it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:03, 42.17it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:03, 42.56it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 43.06it/s]
Loading 0:  62%|██████▏   | 226/363 [00:11<00:03, 44.17it/s]
Loading 0:  64%|██████▎   | 231/363 [00:11<00:03, 35.72it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:02, 42.82it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:02, 42.06it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 41.20it/s]
Loading 0:  70%|██████▉   | 253/363 [00:12<00:02, 43.15it/s]
Loading 0:  71%|███████   | 258/363 [00:12<00:04, 26.06it/s]
Loading 0:  73%|███████▎  | 266/363 [00:12<00:02, 34.32it/s]
Loading 0:  75%|███████▍  | 272/363 [00:13<00:02, 36.01it/s]
Loading 0:  76%|███████▋  | 277/363 [00:13<00:02, 36.38it/s]
Loading 0:  78%|███████▊  | 284/363 [00:13<00:01, 41.72it/s]
Loading 0:  80%|███████▉  | 289/363 [00:13<00:01, 43.03it/s]
Loading 0:  81%|████████  | 294/363 [00:13<00:01, 36.73it/s]
Loading 0:  83%|████████▎ | 301/363 [00:13<00:01, 43.84it/s]
Loading 0:  84%|████████▍ | 306/363 [00:13<00:01, 43.11it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 43.79it/s]
Loading 0:  87%|████████▋ | 317/363 [00:14<00:01, 42.21it/s]
Loading 0:  89%|████████▊ | 322/363 [00:14<00:00, 41.40it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:00, 44.51it/s]
Loading 0:  92%|█████████▏| 333/363 [00:14<00:00, 43.95it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 42.88it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 43.85it/s]
Loading 0:  96%|█████████▌| 348/363 [00:14<00:00, 36.68it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 31.51it/s]
Loading 0:  99%|█████████▉| 359/363 [00:15<00:00, 32.07it/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-v5-v1-mkmlizer:   warnings.warn(
sao10k-nemo-rp-v5-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-v5-v1-mkmlizer:   warnings.warn(
sao10k-nemo-rp-v5-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-v5-v1-mkmlizer:   warnings.warn(
sao10k-nemo-rp-v5-v1-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.21s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  3.88s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.08s/it]
sao10k-nemo-rp-v5-v1-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.38it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.88it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.55it/s]
sao10k-nemo-rp-v5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-nemo-rp-v5-v1-mkmlizer: Saving duration: 1.382s
sao10k-nemo-rp-v5-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.053s
sao10k-nemo-rp-v5-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-nemo-rp-v5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-nemo-rp-v5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-nemo-rp-v5-v1_reward
sao10k-nemo-rp-v5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-nemo-rp-v5-v1_reward/config.json
sao10k-nemo-rp-v5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-nemo-rp-v5-v1_reward/special_tokens_map.json
sao10k-nemo-rp-v5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-nemo-rp-v5-v1_reward/tokenizer_config.json
sao10k-nemo-rp-v5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-nemo-rp-v5-v1_reward/merges.txt
sao10k-nemo-rp-v5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-nemo-rp-v5-v1_reward/vocab.json
sao10k-nemo-rp-v5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-nemo-rp-v5-v1_reward/tokenizer.json
sao10k-nemo-rp-v5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-nemo-rp-v5-v1_reward/reward.tensors
Job sao10k-nemo-rp-v5-v1-mkmlizer completed after 135.93s with status: succeeded
Stopping job with name sao10k-nemo-rp-v5-v1-mkmlizer
Pipeline stage MKMLizer completed in 136.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-nemo-rp-v5-v1
Waiting for inference service sao10k-nemo-rp-v5-v1 to be ready
Inference service sao10k-nemo-rp-v5-v1 ready after 130.82653903961182s
Pipeline stage ISVCDeployer completed in 132.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.55877947807312s
Received healthy response to inference request in 1.738327980041504s
Received healthy response to inference request in 1.736717700958252s
Received healthy response to inference request in 1.7496650218963623s
Received healthy response to inference request in 1.7388105392456055s
5 requests
0 failed requests
5th percentile: 1.7370397567749023
10th percentile: 1.7373618125915526
20th percentile: 1.7380059242248536
30th percentile: 1.7384244918823242
40th percentile: 1.738617515563965
50th percentile: 1.7388105392456055
60th percentile: 1.7431523323059082
70th percentile: 1.7474941253662108
80th percentile: 1.911487913131714
90th percentile: 2.235133695602417
95th percentile: 2.3969565868377685
99th percentile: 2.5264148998260496
mean time: 1.9044601440429687
Pipeline stage StressChecker completed in 10.50s
sao10k-nemo-rp-v5_v1 status is now deployed due to DeploymentManager action
sao10k-nemo-rp-v5_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-nemo-rp-v5_v1
Running pipeline stage ISVCDeleter
Checking if service sao10k-nemo-rp-v5-v1 is running
Tearing down inference service sao10k-nemo-rp-v5-v1
Service sao10k-nemo-rp-v5-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.62s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-nemo-rp-v5-v1/config.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v5-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v5-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v5-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v5-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-nemo-rp-v5-v1_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v5-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v5-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v5-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v5-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v5-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v5-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.94s
sao10k-nemo-rp-v5_v1 status is now torndown due to DeploymentManager action