sao10k-nemo-rp-v2

developer_uid: sao10k

submission_id: sao10k-nemo-rp-v2_v2

model_name: Nemo-RP-Iteration-2

model_group: Sao10K/Nemo-RP-v2

status: torndown

timestamp: 2024-08-01T10:58:00+00:00

num_battles: 17527

num_wins: 9254

celo_rating: 1229.04

family_friendly_score: 0.0

submission_type: basic

model_repo: Sao10K/Nemo-RP-v2

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-2

is_internal_developer: False

language_model: Sao10K/Nemo-RP-v2

model_size: 13B

ranking_group: single

us_pacific_date: 2024-08-01

win_ratio: 0.527985393963599

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-v2-v2-mkmlizer
Waiting for job on sao10k-nemo-rp-v2-v2-mkmlizer to finish
sao10k-nemo-rp-v2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-nemo-rp-v2-v2-mkmlizer: ║     _____            __           __                                ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║       /___/                                                         ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║  Version: 0.9.7                                                     ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║  belonging to:                                                      ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-nemo-rp-v2-v2-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-nemo-rp-v2-v2-mkmlizer: Downloaded to shared memory in 30.436s
sao10k-nemo-rp-v2-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjymdcoke, device:0
sao10k-nemo-rp-v2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-nemo-rp-v2-v2-mkmlizer: quantized model in 36.735s
sao10k-nemo-rp-v2-v2-mkmlizer: Processed model Sao10K/Nemo-RP-v2 in 67.172s
sao10k-nemo-rp-v2-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-nemo-rp-v2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-nemo-rp-v2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-nemo-rp-v2-v2
sao10k-nemo-rp-v2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-nemo-rp-v2-v2/config.json
sao10k-nemo-rp-v2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-nemo-rp-v2-v2/special_tokens_map.json
sao10k-nemo-rp-v2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-nemo-rp-v2-v2/tokenizer_config.json
sao10k-nemo-rp-v2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-nemo-rp-v2-v2/tokenizer.json
sao10k-nemo-rp-v2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-nemo-rp-v2-v2/flywheel_model.0.safetensors
sao10k-nemo-rp-v2-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
sao10k-nemo-rp-v2-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:18,  3.04s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:52,  1.22it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:44,  3.35it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:10,  4.89it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:42,  7.98it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:29, 11.42it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:22, 14.56it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:16, 19.57it/s]
Loading 0:  12%|█▏        | 45/363 [00:07<00:13, 23.18it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:11, 26.47it/s]
Loading 0:  15%|█▌        | 55/363 [00:07<00:10, 30.61it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:14, 20.97it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:10, 28.10it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:09, 30.21it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:08, 33.01it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:07, 36.18it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 32.63it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 40.52it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 40.13it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:06, 41.28it/s]
Loading 0:  30%|███       | 109/363 [00:08<00:05, 43.14it/s]
Loading 0:  31%|███▏      | 114/363 [00:09<00:06, 36.56it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:05, 44.36it/s]
Loading 0:  35%|███▍      | 127/363 [00:09<00:05, 44.97it/s]
Loading 0:  36%|███▋      | 132/363 [00:09<00:06, 36.30it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:05, 42.97it/s]
Loading 0:  40%|███▉      | 144/363 [00:09<00:05, 41.99it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:05, 42.28it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:04, 44.17it/s]
Loading 0:  44%|████▍     | 159/363 [00:10<00:07, 25.67it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:06, 32.02it/s]
Loading 0:  47%|████▋     | 171/363 [00:10<00:05, 33.04it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:05, 34.48it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:05, 35.40it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:04, 37.04it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:04, 39.34it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:05, 33.47it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:03, 40.92it/s]
Loading 0:  57%|█████▋    | 207/363 [00:11<00:03, 40.30it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:03, 40.45it/s]
Loading 0:  60%|█████▉    | 217/363 [00:11<00:03, 41.29it/s]
Loading 0:  61%|██████    | 222/363 [00:11<00:04, 34.20it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 40.79it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:03, 40.60it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:03, 40.71it/s]
Loading 0:  67%|██████▋   | 244/363 [00:12<00:02, 42.29it/s]
Loading 0:  69%|██████▊   | 249/363 [00:12<00:03, 35.59it/s]
Loading 0:  71%|███████   | 256/363 [00:12<00:03, 29.61it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:03, 30.32it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:02, 34.89it/s]
Loading 0:  75%|███████▍  | 271/363 [00:13<00:02, 37.77it/s]
Loading 0:  76%|███████▌  | 276/363 [00:13<00:02, 33.98it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:01, 41.58it/s]
Loading 0:  79%|███████▉  | 288/363 [00:13<00:01, 42.41it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 42.18it/s]
Loading 0:  82%|████████▏ | 298/363 [00:13<00:01, 42.95it/s]
Loading 0:  83%|████████▎ | 303/363 [00:14<00:01, 35.72it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 42.79it/s]
Loading 0:  87%|████████▋ | 315/363 [00:14<00:01, 42.22it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:01, 42.51it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:00, 43.33it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:00, 35.53it/s]
Loading 0:  93%|█████████▎| 337/363 [00:14<00:00, 42.72it/s]
Loading 0:  94%|█████████▍| 342/363 [00:14<00:00, 42.08it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 41.48it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 42.30it/s]
Loading 0:  98%|█████████▊| 357/363 [00:15<00:00, 24.32it/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-v2-v2-mkmlizer:   warnings.warn(
sao10k-nemo-rp-v2-v2-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-v2-v2-mkmlizer:   warnings.warn(
sao10k-nemo-rp-v2-v2-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-v2-v2-mkmlizer:   warnings.warn(
sao10k-nemo-rp-v2-v2-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.32s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  3.80s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.03s/it]
sao10k-nemo-rp-v2-v2-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.29it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.75it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.42it/s]
sao10k-nemo-rp-v2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-nemo-rp-v2-v2-mkmlizer: Saving duration: 1.352s
sao10k-nemo-rp-v2-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.122s
sao10k-nemo-rp-v2-v2-mkmlizer: creating bucket guanaco-reward-models
sao10k-nemo-rp-v2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-nemo-rp-v2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-nemo-rp-v2-v2_reward
sao10k-nemo-rp-v2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-nemo-rp-v2-v2_reward/config.json
sao10k-nemo-rp-v2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-nemo-rp-v2-v2_reward/tokenizer_config.json
sao10k-nemo-rp-v2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-nemo-rp-v2-v2_reward/special_tokens_map.json
sao10k-nemo-rp-v2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-nemo-rp-v2-v2_reward/merges.txt
sao10k-nemo-rp-v2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-nemo-rp-v2-v2_reward/vocab.json
sao10k-nemo-rp-v2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-nemo-rp-v2-v2_reward/tokenizer.json
sao10k-nemo-rp-v2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-nemo-rp-v2-v2_reward/reward.tensors
Job sao10k-nemo-rp-v2-v2-mkmlizer completed after 117.04s with status: succeeded
Stopping job with name sao10k-nemo-rp-v2-v2-mkmlizer
Pipeline stage MKMLizer completed in 118.59s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-nemo-rp-v2-v2
Waiting for inference service sao10k-nemo-rp-v2-v2 to be ready
Inference service sao10k-nemo-rp-v2-v2 ready after 131.12186670303345s
Pipeline stage ISVCDeployer completed in 133.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.549858331680298s
Received healthy response to inference request in 1.7566683292388916s
Received healthy response to inference request in 1.7509543895721436s
Received healthy response to inference request in 1.7597334384918213s
Received healthy response to inference request in 1.7431089878082275s
5 requests
0 failed requests
5th percentile: 1.7446780681610108
10th percentile: 1.746247148513794
20th percentile: 1.7493853092193603
30th percentile: 1.7520971775054932
40th percentile: 1.7543827533721923
50th percentile: 1.7566683292388916
60th percentile: 1.7578943729400636
70th percentile: 1.7591204166412353
80th percentile: 1.9177584171295168
90th percentile: 2.2338083744049073
95th percentile: 2.3918333530426024
99th percentile: 2.5182533359527586
mean time: 1.9120646953582763
Pipeline stage StressChecker completed in 10.33s
sao10k-nemo-rp-v2_v2 status is now deployed due to DeploymentManager action
sao10k-nemo-rp-v2_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-nemo-rp-v2_v2
Running pipeline stage ISVCDeleter
Checking if service sao10k-nemo-rp-v2-v2 is running
Tearing down inference service sao10k-nemo-rp-v2-v2
Service sao10k-nemo-rp-v2-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.49s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-nemo-rp-v2-v2/config.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v2-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v2-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v2-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v2-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-nemo-rp-v2-v2_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v2-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v2-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v2-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v2-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v2-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v2-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.54s
sao10k-nemo-rp-v2_v2 status is now torndown due to DeploymentManager action