submission_id: zonemercy-acute-nemo-v1-_7579_v1
developer_uid: zonemercy
alignment_samples: 10180
alignment_score: 4.86242531910885
best_of: 16
celo_rating: 1244.22
display_name: 0814v1-1
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
language_model: zonemercy/Acute-Nemo-v1-5e6ep1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: zonemercy/Acute-Nemo-v1-
model_name: 0814v1-1
model_num_parameters: 12772070400.0
model_repo: zonemercy/Acute-Nemo-v1-5e6ep1
model_size: 13B
num_battles: 10180
num_wins: 5302
propriety_score: 0.7380434782608696
propriety_total_count: 920.0
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-15T00:25:57+00:00
us_pacific_date: 2024-08-14
win_ratio: 0.5208251473477407
Download Preferencedata
Resubmit model
Running pipeline stage MKMLizer
Starting job with name zonemercy-acute-nemo-v1-7579-v1-mkmlizer
Waiting for job on zonemercy-acute-nemo-v1-7579-v1-mkmlizer to finish
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ _____ __ __ ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ /___/ ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ Version: 0.9.9 ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ https://mk1.ai ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ belonging to: ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ Chai Research Corp. ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ║ ║
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: Downloaded to shared memory in 113.122s
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgnlh66pi, device:0
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: quantized model in 40.950s
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: Processed model zonemercy/Acute-Nemo-v1-5e6ep1 in 154.072s
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-acute-nemo-v1-7579-v1
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-acute-nemo-v1-7579-v1/special_tokens_map.json
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-acute-nemo-v1-7579-v1/config.json
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-acute-nemo-v1-7579-v1/tokenizer_config.json
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-acute-nemo-v1-7579-v1/tokenizer.json
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-acute-nemo-v1-7579-v1/flywheel_model.0.safetensors
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:15, 22.50it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:12, 28.19it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:14, 24.41it/s] Loading 0: 6%|▌ | 20/363 [00:00<00:10, 33.23it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:14, 23.63it/s] Loading 0: 7%|▋ | 27/363 [00:01<00:14, 22.66it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:12, 25.94it/s] Loading 0: 9%|▉ | 34/363 [00:01<00:12, 25.56it/s] Loading 0: 11%|█ | 39/363 [00:01<00:11, 29.04it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:11, 27.97it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:10, 30.37it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:11, 28.08it/s] Loading 0: 15%|█▌ | 56/363 [00:02<00:10, 28.91it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:11, 25.44it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:13, 22.39it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:10, 29.05it/s] Loading 0: 21%|██ | 75/363 [00:02<00:10, 28.18it/s] Loading 0: 21%|██▏ | 78/363 [00:02<00:10, 26.21it/s] Loading 0: 23%|██▎ | 84/363 [00:03<00:09, 30.38it/s] Loading 0: 24%|██▍ | 88/363 [00:03<00:09, 28.69it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:08, 30.85it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:09, 29.41it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:11, 23.04it/s] Loading 0: 29%|██▊ | 104/363 [00:03<00:12, 20.62it/s] Loading 0: 31%|███ | 111/363 [00:04<00:09, 27.53it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:09, 27.05it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 29.55it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 27.97it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 30.29it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:07, 28.98it/s] Loading 0: 38%|███▊ | 137/363 [00:05<00:07, 29.34it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 25.78it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:08, 24.26it/s] Loading 0: 41%|████ | 149/363 [00:05<00:09, 22.94it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:07, 29.47it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:07, 28.22it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:06, 30.41it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 28.86it/s] Loading 0: 47%|████▋ | 172/363 [00:06<00:06, 29.07it/s] Loading 0: 48%|████▊ | 176/363 [00:06<00:07, 25.90it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:07, 24.99it/s] Loading 0: 51%|█████ | 185/363 [00:06<00:08, 21.98it/s] Loading 0: 53%|█████▎ | 192/363 [00:07<00:06, 28.39it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:06, 27.44it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 29.98it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 28.20it/s] Loading 0: 58%|█████▊ | 210/363 [00:07<00:05, 29.95it/s] Loading 0: 59%|█████▉ | 214/363 [00:07<00:05, 28.55it/s] Loading 0: 60%|██████ | 218/363 [00:07<00:05, 28.38it/s] Loading 0: 61%|██████▏ | 223/363 [00:08<00:05, 24.72it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:05, 23.51it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:05, 22.24it/s] Loading 0: 65%|██████▌ | 237/363 [00:08<00:04, 28.92it/s] Loading 0: 66%|██████▋ | 241/363 [00:08<00:04, 27.74it/s] Loading 0: 68%|██████▊ | 246/363 [00:09<00:03, 29.58it/s] Loading 0: 69%|██████▉ | 250/363 [00:09<00:03, 28.33it/s] Loading 0: 70%|███████ | 255/363 [00:09<00:03, 30.61it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 29.07it/s] Loading 0: 72%|███████▏ | 263/363 [00:09<00:04, 23.58it/s] Loading 0: 73%|███████▎ | 266/363 [00:09<00:04, 20.72it/s] Loading 0: 75%|███████▌ | 273/363 [00:10<00:03, 27.44it/s] Loading 0: 76%|███████▌ | 276/363 [00:10<00:03, 25.55it/s] Loading 0: 78%|███████▊ | 282/363 [00:10<00:02, 29.84it/s] Loading 0: 79%|███████▉ | 286/363 [00:10<00:02, 28.57it/s] Loading 0: 80%|████████ | 291/363 [00:10<00:02, 30.37it/s] Loading 0: 81%|████████▏ | 295/363 [00:10<00:02, 28.81it/s] Loading 0: 82%|████████▏ | 299/363 [00:10<00:02, 28.71it/s] Loading 0: 84%|████████▎ | 304/363 [00:11<00:02, 24.76it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 23.51it/s] Loading 0: 86%|████████▌ | 311/363 [00:11<00:02, 22.54it/s] Loading 0: 88%|████████▊ | 318/363 [00:11<00:01, 29.05it/s] Loading 0: 89%|████████▊ | 322/363 [00:11<00:01, 28.00it/s] Loading 0: 90%|█████████ | 327/363 [00:12<00:01, 30.40it/s] Loading 0: 91%|█████████ | 331/363 [00:12<00:01, 28.94it/s] Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 31.27it/s] Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 29.70it/s] Loading 0: 95%|█████████▍| 344/363 [00:19<00:09, 1.97it/s] Loading 0: 96%|█████████▌| 348/363 [00:19<00:05, 2.65it/s] Loading 0: 97%|█████████▋| 353/363 [00:19<00:02, 3.85it/s] Loading 0: 98%|█████████▊| 357/363 [00:19<00:01, 5.00it/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.
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: warnings.warn(
zonemercy-acute-nemo-v1-7579-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.
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: warnings.warn(
zonemercy-acute-nemo-v1-7579-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.
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: warnings.warn(
Failed to get response for submission zonemercy-burly-blue-cp2500_v5: ('http://zonemercy-burly-blue-cp2500-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:35048->127.0.0.1:8080: read: connection reset by peer\n')
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.79s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.14s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.39s/it]
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.21it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.68it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.34it/s]
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: Saving duration: 1.331s
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.972s
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: creating bucket guanaco-reward-models
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/zonemercy-acute-nemo-v1-7579-v1_reward
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/zonemercy-acute-nemo-v1-7579-v1_reward/config.json
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/zonemercy-acute-nemo-v1-7579-v1_reward/special_tokens_map.json
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/zonemercy-acute-nemo-v1-7579-v1_reward/tokenizer_config.json
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/zonemercy-acute-nemo-v1-7579-v1_reward/merges.txt
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/zonemercy-acute-nemo-v1-7579-v1_reward/vocab.json
zonemercy-acute-nemo-v1-7579-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/zonemercy-acute-nemo-v1-7579-v1_reward/tokenizer.json
Job zonemercy-acute-nemo-v1-7579-v1-mkmlizer completed after 200.02s with status: succeeded
Stopping job with name zonemercy-acute-nemo-v1-7579-v1-mkmlizer
Pipeline stage MKMLizer completed in 200.47s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service zonemercy-acute-nemo-v1-7579-v1
Waiting for inference service zonemercy-acute-nemo-v1-7579-v1 to be ready
Inference service zonemercy-acute-nemo-v1-7579-v1 ready after 221.33799624443054s
Pipeline stage ISVCDeployer completed in 222.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7903339862823486s
Received healthy response to inference request in 1.746762752532959s
Received healthy response to inference request in 1.7719669342041016s
Received healthy response to inference request in 1.7314813137054443s
Received healthy response to inference request in 1.7673485279083252s
5 requests
0 failed requests
5th percentile: 1.7345376014709473
10th percentile: 1.7375938892364502
20th percentile: 1.743706464767456
30th percentile: 1.7508799076080321
40th percentile: 1.7591142177581787
50th percentile: 1.7673485279083252
60th percentile: 1.7691958904266358
70th percentile: 1.7710432529449462
80th percentile: 1.9756403446197512
90th percentile: 2.3829871654510497
95th percentile: 2.586660575866699
99th percentile: 2.7495993041992186
mean time: 1.9615787029266358
Pipeline stage StressChecker completed in 10.47s
zonemercy-acute-nemo-v1-_7579_v1 status is now deployed due to DeploymentManager action
zonemercy-acute-nemo-v1-_7579_v1 status is now inactive due to auto deactivation removed underperforming models
zonemercy-acute-nemo-v1-_7579_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics