sao10k-nemo-rp-v6

developer_uid: sao10k

submission_id: sao10k-nemo-rp-v6_v1

model_name: Nemo-RP-Iteration-6

model_group: Sao10K/Nemo-RP-v6

status: torndown

timestamp: 2024-08-02T10:35:27+00:00

num_battles: 10433

num_wins: 5601

celo_rating: 1224.45

family_friendly_score: 0.0

submission_type: basic

model_repo: Sao10K/Nemo-RP-v6

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-6

is_internal_developer: False

language_model: Sao10K/Nemo-RP-v6

model_size: 13B

ranking_group: single

us_pacific_date: 2024-08-02

win_ratio: 0.5368542125946516

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-v6-v1-mkmlizer
Waiting for job on sao10k-nemo-rp-v6-v1-mkmlizer to finish
sao10k-nemo-rp-v6-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-nemo-rp-v6-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║       /___/                                                         ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║  Version: 0.9.9                                                     ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-nemo-rp-v6-v1-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v6-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-nemo-rp-v6-v1-mkmlizer: Downloaded to shared memory in 32.848s
sao10k-nemo-rp-v6-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpddkkq44t, device:0
sao10k-nemo-rp-v6-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-nemo-rp-v6-v1-mkmlizer: quantized model in 36.059s
sao10k-nemo-rp-v6-v1-mkmlizer: Processed model Sao10K/Nemo-RP-v6 in 68.907s
sao10k-nemo-rp-v6-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-nemo-rp-v6-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-nemo-rp-v6-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-nemo-rp-v6-v1
sao10k-nemo-rp-v6-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-nemo-rp-v6-v1/config.json
sao10k-nemo-rp-v6-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-nemo-rp-v6-v1/special_tokens_map.json
sao10k-nemo-rp-v6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-nemo-rp-v6-v1/tokenizer_config.json
sao10k-nemo-rp-v6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-nemo-rp-v6-v1/tokenizer.json
sao10k-nemo-rp-v6-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-nemo-rp-v6-v1/flywheel_model.0.safetensors
sao10k-nemo-rp-v6-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
sao10k-nemo-rp-v6-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:15,  3.03s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:50,  1.23it/s]
Loading 0:   3%|▎         | 12/363 [00:06<01:54,  3.08it/s]
Loading 0:   4%|▍         | 16/363 [00:06<01:15,  4.62it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:40,  8.32it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:28, 11.77it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:21, 14.97it/s]
Loading 0:  11%|█▏        | 41/363 [00:06<00:15, 20.86it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:12, 24.66it/s]
Loading 0:  14%|█▍        | 52/363 [00:07<00:11, 27.31it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:12, 24.18it/s]
Loading 0:  17%|█▋        | 62/363 [00:07<00:11, 26.10it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:09, 30.30it/s]
Loading 0:  20%|█▉        | 71/363 [00:07<00:09, 31.27it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 36.01it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:07, 39.17it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:07, 34.68it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 43.26it/s]
Loading 0:  28%|██▊       | 100/363 [00:08<00:05, 44.39it/s]
Loading 0:  29%|██▉       | 105/363 [00:08<00:06, 37.50it/s]
Loading 0:  31%|███       | 112/363 [00:08<00:05, 44.49it/s]
Loading 0:  32%|███▏      | 117/363 [00:08<00:05, 44.00it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:05, 44.06it/s]
Loading 0:  35%|███▍      | 127/363 [00:09<00:05, 44.80it/s]
Loading 0:  36%|███▋      | 132/363 [00:09<00:06, 36.64it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:05, 44.06it/s]
Loading 0:  40%|███▉      | 144/363 [00:09<00:05, 43.74it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:04, 43.97it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:04, 45.25it/s]
Loading 0:  44%|████▍     | 159/363 [00:10<00:07, 26.00it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:05, 34.31it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:05, 36.83it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:05, 33.61it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 40.92it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:04, 40.81it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:04, 39.25it/s]
Loading 0:  55%|█████▍    | 199/363 [00:11<00:03, 41.66it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:04, 36.47it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:03, 44.07it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:03, 43.88it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 43.78it/s]
Loading 0:  63%|██████▎   | 227/363 [00:11<00:03, 42.34it/s]
Loading 0:  64%|██████▍   | 232/363 [00:11<00:03, 41.29it/s]
Loading 0:  66%|██████▌   | 238/363 [00:11<00:02, 45.84it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:02, 44.00it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 44.70it/s]
Loading 0:  70%|██████▉   | 254/363 [00:12<00:02, 42.18it/s]
Loading 0:  71%|███████▏  | 259/363 [00:12<00:03, 29.02it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 34.66it/s]
Loading 0:  74%|███████▍  | 270/363 [00:12<00:02, 36.06it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:02, 38.09it/s]
Loading 0:  77%|███████▋  | 280/363 [00:13<00:02, 40.88it/s]
Loading 0:  79%|███████▊  | 285/363 [00:13<00:02, 33.98it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:01, 41.43it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 42.08it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 43.28it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:01, 44.93it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:01, 37.36it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:00, 45.14it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:00, 46.01it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:00, 38.51it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 46.00it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 43.63it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 42.25it/s]
Loading 0:  98%|█████████▊| 355/363 [00:14<00:00, 31.95it/s]
Loading 0:  99%|█████████▉| 359/363 [00:15<00:00, 32.77it/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-v6-v1-mkmlizer:   warnings.warn(
sao10k-nemo-rp-v6-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-v6-v1-mkmlizer:   warnings.warn(
sao10k-nemo-rp-v6-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-v6-v1-mkmlizer:   warnings.warn(
sao10k-nemo-rp-v6-v1-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.35s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  3.92s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.13s/it]
sao10k-nemo-rp-v6-v1-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.42it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.97it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.62it/s]
sao10k-nemo-rp-v6-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-nemo-rp-v6-v1-mkmlizer: Saving duration: 1.393s
sao10k-nemo-rp-v6-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.520s
sao10k-nemo-rp-v6-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-nemo-rp-v6-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-nemo-rp-v6-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-nemo-rp-v6-v1_reward
sao10k-nemo-rp-v6-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-nemo-rp-v6-v1_reward/special_tokens_map.json
sao10k-nemo-rp-v6-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-nemo-rp-v6-v1_reward/config.json
sao10k-nemo-rp-v6-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-nemo-rp-v6-v1_reward/tokenizer_config.json
sao10k-nemo-rp-v6-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-nemo-rp-v6-v1_reward/merges.txt
sao10k-nemo-rp-v6-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-nemo-rp-v6-v1_reward/vocab.json
sao10k-nemo-rp-v6-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-nemo-rp-v6-v1_reward/tokenizer.json
sao10k-nemo-rp-v6-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-nemo-rp-v6-v1_reward/reward.tensors
Job sao10k-nemo-rp-v6-v1-mkmlizer completed after 116.21s with status: succeeded
Stopping job with name sao10k-nemo-rp-v6-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.26s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-nemo-rp-v6-v1
Waiting for inference service sao10k-nemo-rp-v6-v1 to be ready
Inference service sao10k-nemo-rp-v6-v1 ready after 141.2607114315033s
Pipeline stage ISVCDeployer completed in 143.06s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.537205219268799s
Received healthy response to inference request in 1.7433829307556152s
Received healthy response to inference request in 1.7590513229370117s
Received healthy response to inference request in 1.722350835800171s
Received healthy response to inference request in 1.7306513786315918s
5 requests
0 failed requests
5th percentile: 1.724010944366455
10th percentile: 1.7256710529327393
20th percentile: 1.7289912700653076
30th percentile: 1.7331976890563965
40th percentile: 1.7382903099060059
50th percentile: 1.7433829307556152
60th percentile: 1.7496502876281739
70th percentile: 1.7559176445007325
80th percentile: 1.9146821022033693
90th percentile: 2.225943660736084
95th percentile: 2.3815744400024412
99th percentile: 2.506079063415527
mean time: 1.8985283374786377
Pipeline stage StressChecker completed in 10.14s
sao10k-nemo-rp-v6_v1 status is now deployed due to DeploymentManager action
sao10k-nemo-rp-v6_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-nemo-rp-v6_v1
Running pipeline stage ISVCDeleter
Checking if service sao10k-nemo-rp-v6-v1 is running
Tearing down inference service sao10k-nemo-rp-v6-v1
Service sao10k-nemo-rp-v6-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.30s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-nemo-rp-v6-v1/config.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v6-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v6-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v6-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v6-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-nemo-rp-v6-v1_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v6-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v6-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v6-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v6-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v6-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v6-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.26s
sao10k-nemo-rp-v6_v1 status is now torndown due to DeploymentManager action