sao10k-nemo-rp-v3

submission_id: sao10k-nemo-rp-v3_v2

developer_uid: sao10k

best_of: 8

celo_rating: 1210.16

display_name: Nemo-RP-Iteration-3

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-v3

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: Sao10K/Nemo-RP-v3

model_name: Nemo-RP-Iteration-3

model_num_parameters: 12772070400.0

model_repo: Sao10K/Nemo-RP-v3

model_size: 13B

num_battles: 21195

num_wins: 10542

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: 2024-08-01T10:58:10+00:00

us_pacific_date: 2024-08-01

win_ratio: 0.497381457891012

Resubmit model

Running pipeline stage MKMLizer
Starting job with name sao10k-nemo-rp-v3-v2-mkmlizer
Waiting for job on sao10k-nemo-rp-v3-v2-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
sao10k-nemo-rp-v3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-nemo-rp-v3-v2-mkmlizer: ║     _____            __           __                                ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║       /___/                                                         ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║  Version: 0.9.7                                                     ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║  belonging to:                                                      ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-nemo-rp-v3-v2-mkmlizer: ║                                                                     ║
sao10k-nemo-rp-v3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-nemo-rp-v3-v2-mkmlizer: Downloaded to shared memory in 30.550s
sao10k-nemo-rp-v3-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq9l295i8, device:0
sao10k-nemo-rp-v3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-nemo-rp-v3-v2-mkmlizer: quantized model in 36.493s
sao10k-nemo-rp-v3-v2-mkmlizer: Processed model Sao10K/Nemo-RP-v3 in 67.043s
sao10k-nemo-rp-v3-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-nemo-rp-v3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-nemo-rp-v3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-nemo-rp-v3-v2
sao10k-nemo-rp-v3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-nemo-rp-v3-v2/config.json
sao10k-nemo-rp-v3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-nemo-rp-v3-v2/special_tokens_map.json
sao10k-nemo-rp-v3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-nemo-rp-v3-v2/tokenizer_config.json
sao10k-nemo-rp-v3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-nemo-rp-v3-v2/tokenizer.json
sao10k-nemo-rp-v3-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
sao10k-nemo-rp-v3-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:27,  3.07s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:54,  1.21it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:09,  2.72it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:21,  4.25it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:40,  8.45it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:28, 11.77it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:22, 14.87it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:16, 19.97it/s]
Loading 0:  12%|█▏        | 45/363 [00:07<00:13, 23.52it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:11, 26.71it/s]
Loading 0:  15%|█▌        | 55/363 [00:07<00:10, 30.65it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:14, 21.23it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:10, 28.07it/s]
Loading 0:  20%|█▉        | 72/363 [00:08<00:09, 30.73it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:08, 33.48it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:07, 36.37it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 32.05it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 39.67it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 39.53it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:06, 40.57it/s]
Loading 0:  30%|███       | 109/363 [00:08<00:05, 42.57it/s]
Loading 0:  31%|███▏      | 114/363 [00:09<00:06, 35.82it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:05, 42.76it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:05, 42.94it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:05, 43.25it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:05, 44.49it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:06, 36.11it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:04, 43.30it/s]
Loading 0:  42%|████▏     | 153/363 [00:09<00:04, 42.83it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:07, 28.49it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:06, 32.28it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:06, 29.80it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:05, 35.98it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:04, 36.65it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:04, 38.23it/s]
Loading 0:  53%|█████▎    | 191/363 [00:11<00:04, 38.88it/s]
Loading 0:  54%|█████▍    | 196/363 [00:11<00:04, 38.52it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:03, 43.06it/s]
Loading 0:  57%|█████▋    | 207/363 [00:11<00:03, 43.18it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:03, 43.97it/s]
Loading 0:  60%|█████▉    | 217/363 [00:11<00:03, 45.47it/s]
Loading 0:  61%|██████    | 222/363 [00:11<00:03, 36.62it/s]
Loading 0:  63%|██████▎   | 229/363 [00:11<00:03, 43.79it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:03, 42.83it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:02, 42.62it/s]
Loading 0:  67%|██████▋   | 244/363 [00:12<00:02, 43.82it/s]
Loading 0:  69%|██████▊   | 249/363 [00:12<00:03, 36.38it/s]
Loading 0:  71%|███████   | 256/363 [00:12<00:03, 29.33it/s]
Loading 0:  72%|███████▏  | 260/363 [00:12<00:03, 30.42it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:02, 33.74it/s]
Loading 0:  74%|███████▍  | 269/363 [00:13<00:02, 33.42it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 36.79it/s]
Loading 0:  77%|███████▋  | 278/363 [00:13<00:02, 37.02it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 39.18it/s]
Loading 0:  79%|███████▉  | 288/363 [00:13<00:01, 39.46it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 40.75it/s]
Loading 0:  82%|████████▏ | 298/363 [00:13<00:01, 42.52it/s]
Loading 0:  83%|████████▎ | 303/363 [00:14<00:01, 35.79it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 43.34it/s]
Loading 0:  87%|████████▋ | 315/363 [00:14<00:01, 43.31it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:00, 43.44it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:00, 42.56it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:00, 41.44it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 46.17it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 47.04it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 39.41it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 32.00it/s]
Loading 0:  99%|█████████▉| 359/363 [00:15<00:00, 32.60it/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-v3-v2-mkmlizer:   warnings.warn(
sao10k-nemo-rp-v3-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-v3-v2-mkmlizer:   warnings.warn(
sao10k-nemo-rp-v3-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-v3-v2-mkmlizer:   warnings.warn(
sao10k-nemo-rp-v3-v2-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,  4.12s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.31s/it]
sao10k-nemo-rp-v3-v2-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.37it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.90it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.55it/s]
sao10k-nemo-rp-v3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-nemo-rp-v3-v2-mkmlizer: Saving duration: 1.346s
sao10k-nemo-rp-v3-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.589s
sao10k-nemo-rp-v3-v2-mkmlizer: creating bucket guanaco-reward-models
sao10k-nemo-rp-v3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-nemo-rp-v3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-nemo-rp-v3-v2_reward
sao10k-nemo-rp-v3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-nemo-rp-v3-v2_reward/config.json
sao10k-nemo-rp-v3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-nemo-rp-v3-v2_reward/special_tokens_map.json
sao10k-nemo-rp-v3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-nemo-rp-v3-v2_reward/tokenizer_config.json
sao10k-nemo-rp-v3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-nemo-rp-v3-v2_reward/merges.txt
sao10k-nemo-rp-v3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-nemo-rp-v3-v2_reward/vocab.json
sao10k-nemo-rp-v3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-nemo-rp-v3-v2_reward/tokenizer.json
Job sao10k-nemo-rp-v3-v2-mkmlizer completed after 116.37s with status: succeeded
Stopping job with name sao10k-nemo-rp-v3-v2-mkmlizer
Pipeline stage MKMLizer completed in 117.36s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-nemo-rp-v3-v2
Waiting for inference service sao10k-nemo-rp-v3-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service sao10k-nemo-rp-v3-v2 ready after 141.1146845817566s
Pipeline stage ISVCDeployer completed in 143.34s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2370173931121826s
Received healthy response to inference request in 1.7400312423706055s
Received healthy response to inference request in 1.7407050132751465s
Received healthy response to inference request in 1.682586431503296s
Received healthy response to inference request in 1.1191129684448242s
5 requests
0 failed requests
5th percentile: 1.2318076610565185
10th percentile: 1.3445023536682128
20th percentile: 1.5698917388916016
30th percentile: 1.6940753936767579
40th percentile: 1.7170533180236816
50th percentile: 1.7400312423706055
60th percentile: 1.740300750732422
70th percentile: 1.7405702590942382
80th percentile: 1.8399674892425537
90th percentile: 2.038492441177368
95th percentile: 2.1377549171447754
99th percentile: 2.217164897918701
mean time: 1.703890609741211
Pipeline stage StressChecker completed in 9.22s
sao10k-nemo-rp-v3_v2 status is now deployed due to DeploymentManager action
sao10k-nemo-rp-v3_v2 status is now inactive due to auto deactivation removed underperforming models
sao10k-nemo-rp-v3_v2 status is now deployed due to admin request
sao10k-nemo-rp-v3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-nemo-rp-v3_v2
Running pipeline stage ISVCDeleter
Checking if service sao10k-nemo-rp-v3-v2 is running
Tearing down inference service sao10k-nemo-rp-v3-v2
Service sao10k-nemo-rp-v3-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.37s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-nemo-rp-v3-v2/config.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-nemo-rp-v3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-nemo-rp-v3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-nemo-rp-v3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.25s
sao10k-nemo-rp-v3_v2 status is now torndown due to DeploymentManager action