aetherwiing-mn-12b-starc_9812

submission_id: aetherwiing-mn-12b-starc_9812_v1

developer_uid: aetherwiing

best_of: 4

celo_rating: 1218.92

display_name: MN-12B-Starcannon-v1

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': 0.87, 'top_p': 0.81, 'min_p': 0.0, 'top_k': 60, 'presence_penalty': 0.15, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 512}

is_internal_developer: False

language_model: aetherwiing/MN-12B-Starcannon-v1

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: aetherwiing/MN-12B-Starc

model_name: MN-12B-Starcannon-v1

model_num_parameters: 12772070400.0

model_repo: aetherwiing/MN-12B-Starcannon-v1

model_size: 13B

num_battles: 44723

num_wins: 25981

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: 2024-07-29T05:28:29+00:00

us_pacific_date: 2024-07-28

win_ratio: 0.5809315117501062

Download Preference Data

Resubmit model

Running pipeline stage MKMLizer
Starting job with name aetherwiing-mn-12b-starc-9812-v1-mkmlizer
Waiting for job on aetherwiing-mn-12b-starc-9812-v1-mkmlizer to finish
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║     _____            __           __                                ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║       /___/                                                         ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║                                                                     ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║  https://mk1.ai                                                     ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║                                                                     ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║  belonging to:                                                      ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║                                                                     ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║  Chai Research Corp.                                                ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ║                                                                     ║
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: Downloaded to shared memory in 42.201s
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpes17odbw, device:0
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: quantized model in 35.662s
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: Processed model aetherwiing/MN-12B-Starcannon-v1 in 77.863s
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: creating bucket guanaco-mkml-models
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/aetherwiing-mn-12b-starc-9812-v1
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/aetherwiing-mn-12b-starc-9812-v1/config.json
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/aetherwiing-mn-12b-starc-9812-v1/special_tokens_map.json
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/aetherwiing-mn-12b-starc-9812-v1/tokenizer.json
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/aetherwiing-mn-12b-starc-9812-v1/flywheel_model.0.safetensors
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
aetherwiing-mn-12b-starc-9812-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<04:52,  1.22it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:44,  3.36it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:10,  4.91it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:42,  8.02it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:28, 11.64it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:21, 15.03it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:18, 17.18it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 19.76it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 25.31it/s]
Loading 0:  15%|█▌        | 55/363 [00:07<00:10, 29.50it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:10, 28.95it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 36.79it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:07, 37.34it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 38.07it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:07, 39.95it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:07, 34.72it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 43.07it/s]
Loading 0:  28%|██▊       | 101/363 [00:08<00:06, 43.02it/s]
Loading 0:  29%|██▉       | 106/363 [00:08<00:06, 41.84it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 46.65it/s]
Loading 0:  33%|███▎      | 119/363 [00:08<00:05, 45.65it/s]
Loading 0:  34%|███▍      | 124/363 [00:09<00:07, 32.16it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:05, 38.73it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:05, 39.49it/s]
Loading 0:  39%|███▉      | 142/363 [00:09<00:05, 40.28it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:04, 45.70it/s]
Loading 0:  43%|████▎     | 155/363 [00:09<00:04, 44.55it/s]
Loading 0:  44%|████▍     | 160/363 [00:09<00:04, 43.77it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 48.94it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:03, 47.96it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:03, 46.29it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:03, 50.42it/s]
Loading 0:  53%|█████▎    | 191/363 [00:10<00:03, 47.47it/s]
Loading 0:  54%|█████▍    | 196/363 [00:10<00:03, 46.79it/s]
Loading 0:  56%|█████▌    | 202/363 [00:10<00:04, 36.46it/s]
Loading 0:  57%|█████▋    | 207/363 [00:11<00:04, 37.68it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:03, 40.26it/s]
Loading 0:  60%|█████▉    | 217/363 [00:11<00:03, 42.44it/s]
Loading 0:  61%|██████    | 222/363 [00:11<00:03, 37.61it/s]
Loading 0:  63%|██████▎   | 230/363 [00:11<00:02, 45.66it/s]
Loading 0:  65%|██████▌   | 236/363 [00:11<00:02, 44.51it/s]
Loading 0:  66%|██████▋   | 241/363 [00:11<00:02, 43.40it/s]
Loading 0:  68%|██████▊   | 248/363 [00:11<00:02, 47.73it/s]
Loading 0:  70%|██████▉   | 253/363 [00:11<00:02, 47.90it/s]
Loading 0:  71%|███████   | 258/363 [00:12<00:02, 40.11it/s]
Loading 0:  73%|███████▎  | 266/363 [00:12<00:02, 47.03it/s]
Loading 0:  75%|███████▍  | 272/363 [00:12<00:02, 45.13it/s]
Loading 0:  76%|███████▋  | 277/363 [00:12<00:01, 44.47it/s]
Loading 0:  78%|███████▊  | 283/363 [00:12<00:02, 36.00it/s]
Loading 0:  79%|███████▉  | 287/363 [00:12<00:02, 35.98it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 40.76it/s]
Loading 0:  82%|████████▏ | 299/363 [00:13<00:01, 41.25it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:01, 41.15it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 46.12it/s]
Loading 0:  87%|████████▋ | 317/363 [00:13<00:01, 45.18it/s]
Loading 0:  89%|████████▊ | 322/363 [00:13<00:00, 43.16it/s]
Loading 0:  90%|█████████ | 328/363 [00:13<00:00, 46.82it/s]
Loading 0:  92%|█████████▏| 333/363 [00:13<00:00, 46.92it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:00, 41.84it/s]
Loading 0:  96%|█████████▌| 347/363 [00:14<00:00, 48.77it/s]
Loading 0:  97%|█████████▋| 353/363 [00:14<00:00, 46.58it/s]
Loading 0:  99%|█████████▊| 358/363 [00:14<00:00, 45.92it/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.
aetherwiing-mn-12b-starc-9812-v1-mkmlizer:   warnings.warn(
aetherwiing-mn-12b-starc-9812-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.
aetherwiing-mn-12b-starc-9812-v1-mkmlizer:   warnings.warn(
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.27s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  3.89s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.10s/it]
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.41it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  4.01it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.64it/s]
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: Saving duration: 1.308s
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.085s
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: creating bucket guanaco-reward-models
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/aetherwiing-mn-12b-starc-9812-v1_reward
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/aetherwiing-mn-12b-starc-9812-v1_reward/config.json
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/aetherwiing-mn-12b-starc-9812-v1_reward/special_tokens_map.json
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/aetherwiing-mn-12b-starc-9812-v1_reward/tokenizer_config.json
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/aetherwiing-mn-12b-starc-9812-v1_reward/merges.txt
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/aetherwiing-mn-12b-starc-9812-v1_reward/vocab.json
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/aetherwiing-mn-12b-starc-9812-v1_reward/tokenizer.json
aetherwiing-mn-12b-starc-9812-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/aetherwiing-mn-12b-starc-9812-v1_reward/reward.tensors
Job aetherwiing-mn-12b-starc-9812-v1-mkmlizer completed after 128.76s with status: succeeded
Stopping job with name aetherwiing-mn-12b-starc-9812-v1-mkmlizer
Pipeline stage MKMLizer completed in 129.71s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service aetherwiing-mn-12b-starc-9812-v1
Waiting for inference service aetherwiing-mn-12b-starc-9812-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service aetherwiing-mn-12b-starc-9812-v1 ready after 110.95973348617554s
Pipeline stage ISVCDeployer completed in 112.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.431644916534424s
Received healthy response to inference request in 1.6055049896240234s
Received healthy response to inference request in 1.5395359992980957s
Received healthy response to inference request in 1.5804400444030762s
Received healthy response to inference request in 1.5902149677276611s
5 requests
0 failed requests
5th percentile: 1.5477168083190918
10th percentile: 1.5558976173400878
20th percentile: 1.5722592353820801
30th percentile: 1.5823950290679931
40th percentile: 1.5863049983978272
50th percentile: 1.5902149677276611
60th percentile: 1.5963309764862061
70th percentile: 1.602446985244751
80th percentile: 1.7707329750061036
90th percentile: 2.101188945770264
95th percentile: 2.2664169311523437
99th percentile: 2.398599319458008
mean time: 1.7494681835174561
Pipeline stage StressChecker completed in 9.37s
aetherwiing-mn-12b-starc_9812_v1 status is now deployed due to DeploymentManager action
aetherwiing-mn-12b-starc_9812_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of aetherwiing-mn-12b-starc_9812_v1
Running pipeline stage ISVCDeleter
Checking if service aetherwiing-mn-12b-starc-9812-v1 is running
Tearing down inference service aetherwiing-mn-12b-starc-9812-v1
Service aetherwiing-mn-12b-starc-9812-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.45s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key aetherwiing-mn-12b-starc-9812-v1/config.json from bucket guanaco-mkml-models
Deleting key aetherwiing-mn-12b-starc-9812-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key aetherwiing-mn-12b-starc-9812-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key aetherwiing-mn-12b-starc-9812-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key aetherwiing-mn-12b-starc-9812-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key aetherwiing-mn-12b-starc-9812-v1_reward/config.json from bucket guanaco-reward-models
Deleting key aetherwiing-mn-12b-starc-9812-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key aetherwiing-mn-12b-starc-9812-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key aetherwiing-mn-12b-starc-9812-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key aetherwiing-mn-12b-starc-9812-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key aetherwiing-mn-12b-starc-9812-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key aetherwiing-mn-12b-starc-9812-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.10s
aetherwiing-mn-12b-starc_9812_v1 status is now torndown due to DeploymentManager action
admin requested tearing down of aetherwiing-mn-12b-starc_9812_v1
Running pipeline stage ISVCDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage ISVCDeleter completed in 0.54s
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLModelDeleter completed in 0.34s
aetherwiing-mn-12b-starc_9812_v1 status is now torndown due to DeploymentManager action