submission_id: zonemercy-acute-nemo-v1-_2373_v2
developer_uid: zonemercy
alignment_samples: 15630
alignment_score: 0.539153324967344
best_of: 16
celo_rating: 1240.65
display_name: zonemercy-acute-nemo-v1-_2373_v2
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': 0.08, '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-v1.1-orpo-5e6ep2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: zonemercy/Acute-Nemo-v1.
model_name: zonemercy-acute-nemo-v1-_2373_v2
model_num_parameters: 12772070400.0
model_repo: zonemercy/Acute-Nemo-v1.1-orpo-5e6ep2
model_size: 13B
num_battles: 15630
num_wins: 8203
propriety_score: 0.718887262079063
propriety_total_count: 1366.0
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-14T23:09:21+00:00
us_pacific_date: 2024-08-14
win_ratio: 0.5248240563019834
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name zonemercy-acute-nemo-v1-2373-v2-mkmlizer
Waiting for job on zonemercy-acute-nemo-v1-2373-v2-mkmlizer to finish
Stopping job with name zonemercy-acute-nemo-v1-2373-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name zonemercy-acute-nemo-v1-2373-v2-mkmlizer
Waiting for job on zonemercy-acute-nemo-v1-2373-v2-mkmlizer to finish
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ _____ __ __ ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ /___/ ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ Version: 0.9.9 ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ https://mk1.ai ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ belonging to: ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ Chai Research Corp. ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ║ ║
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: Downloaded to shared memory in 60.893s
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdwgepq5v, device:0
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: quantized model in 41.564s
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: Processed model zonemercy/Acute-Nemo-v1.1-orpo-5e6ep2 in 102.458s
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-acute-nemo-v1-2373-v2
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-acute-nemo-v1-2373-v2/config.json
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-acute-nemo-v1-2373-v2/special_tokens_map.json
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-acute-nemo-v1-2373-v2/tokenizer_config.json
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-acute-nemo-v1-2373-v2/tokenizer.json
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-acute-nemo-v1-2373-v2/flywheel_model.0.safetensors
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 22.24it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:12, 28.21it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:14, 24.50it/s] Loading 0: 6%|▌ | 20/363 [00:00<00:10, 33.68it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:14, 22.95it/s] Loading 0: 7%|▋ | 27/363 [00:01<00:15, 21.98it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:13, 25.41it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:12, 26.50it/s] Loading 0: 11%|█ | 39/363 [00:01<00:11, 27.12it/s] Loading 0: 12%|█▏ | 42/363 [00:01<00:13, 24.40it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:10, 29.17it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:11, 27.82it/s] Loading 0: 15%|█▌ | 56/363 [00:02<00:11, 27.54it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:12, 24.00it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:14, 20.73it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:10, 27.35it/s] Loading 0: 20%|██ | 74/363 [00:02<00:10, 27.40it/s] Loading 0: 21%|██ | 77/363 [00:03<00:12, 22.56it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:10, 27.81it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:11, 24.78it/s] Loading 0: 25%|██▌ | 91/363 [00:03<00:09, 29.59it/s] Loading 0: 26%|██▌ | 95/363 [00:03<00:10, 25.78it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:10, 24.41it/s] Loading 0: 29%|██▊ | 104/363 [00:04<00:12, 21.17it/s] Loading 0: 31%|███ | 111/363 [00:04<00:09, 27.78it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:09, 27.13it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 29.41it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 28.17it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 30.43it/s] Loading 0: 37%|███▋ | 133/363 [00:05<00:08, 28.16it/s] Loading 0: 38%|███▊ | 137/363 [00:05<00:08, 28.23it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 24.56it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:09, 23.23it/s] Loading 0: 41%|████ | 149/363 [00:05<00:09, 22.35it/s] Loading 0: 42%|████▏ | 154/363 [00:05<00:07, 27.59it/s] Loading 0: 44%|████▎ | 158/363 [00:06<00:08, 24.65it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:06, 30.80it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 28.94it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 30.39it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 28.74it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:07, 23.20it/s] Loading 0: 51%|█████ | 185/363 [00:07<00:08, 20.79it/s] Loading 0: 53%|█████▎ | 192/363 [00:07<00:06, 27.31it/s] Loading 0: 54%|█████▎ | 195/363 [00:07<00:06, 25.36it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 29.93it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 28.14it/s] Loading 0: 58%|█████▊ | 210/363 [00:07<00:05, 29.89it/s] Loading 0: 59%|█████▉ | 214/363 [00:08<00:05, 28.56it/s] Loading 0: 60%|██████ | 218/363 [00:08<00:05, 28.54it/s] Loading 0: 61%|██████▏ | 223/363 [00:08<00:05, 24.74it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:05, 23.50it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:05, 22.20it/s] Loading 0: 65%|██████▌ | 237/363 [00:08<00:04, 28.89it/s] Loading 0: 66%|██████▋ | 241/363 [00:09<00:04, 27.73it/s] Loading 0: 68%|██████▊ | 246/363 [00:09<00:04, 29.12it/s] Loading 0: 69%|██████▉ | 250/363 [00:09<00:04, 28.05it/s] Loading 0: 70%|███████ | 255/363 [00:09<00:03, 30.41it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 28.51it/s] Loading 0: 72%|███████▏ | 263/363 [00:10<00:04, 23.54it/s] Loading 0: 73%|███████▎ | 266/363 [00:10<00:04, 20.77it/s] Loading 0: 75%|███████▍ | 271/363 [00:10<00:03, 26.03it/s] Loading 0: 76%|███████▌ | 275/363 [00:10<00:03, 23.98it/s] Loading 0: 78%|███████▊ | 282/363 [00:10<00:02, 30.06it/s] Loading 0: 79%|███████▉ | 286/363 [00:10<00:02, 28.28it/s] Loading 0: 80%|████████ | 291/363 [00:10<00:02, 30.39it/s] Loading 0: 81%|████████▏ | 295/363 [00:11<00:02, 28.61it/s] Loading 0: 82%|████████▏ | 299/363 [00:11<00:02, 28.41it/s] Loading 0: 84%|████████▎ | 304/363 [00:11<00:02, 24.18it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 22.89it/s] Loading 0: 85%|████████▌ | 310/363 [00:11<00:02, 24.19it/s] Loading 0: 86%|████████▌ | 313/363 [00:11<00:02, 24.32it/s] Loading 0: 88%|████████▊ | 318/363 [00:12<00:01, 27.45it/s] Loading 0: 88%|████████▊ | 321/363 [00:12<00:01, 24.73it/s] Loading 0: 90%|█████████ | 327/363 [00:12<00:01, 29.46it/s] Loading 0: 91%|█████████ | 330/363 [00:12<00:01, 26.41it/s] Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 30.66it/s] Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 28.48it/s] Loading 0: 95%|█████████▍| 344/363 [00:19<00:09, 1.93it/s] Loading 0: 96%|█████████▌| 348/363 [00:20<00:05, 2.59it/s] Loading 0: 97%|█████████▋| 353/363 [00:20<00:02, 3.77it/s] Loading 0: 98%|█████████▊| 357/363 [00:20<00:01, 4.88it/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-v1-2373-v2-mkmlizer: warnings.warn(
zonemercy-acute-nemo-v1-2373-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.
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: warnings.warn(
zonemercy-acute-nemo-v1-2373-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.
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: warnings.warn(
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.78s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.23s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.47s/it]
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.45it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.98it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.64it/s]
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: Saving duration: 1.366s
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.988s
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: creating bucket guanaco-reward-models
zonemercy-acute-nemo-v1-2373-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/zonemercy-acute-nemo-v1-2373-v2_reward/reward.tensors
Job zonemercy-acute-nemo-v1-2373-v2-mkmlizer completed after 167.31s with status: succeeded
Stopping job with name zonemercy-acute-nemo-v1-2373-v2-mkmlizer
Pipeline stage MKMLizer completed in 168.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service zonemercy-acute-nemo-v1-2373-v2
Waiting for inference service zonemercy-acute-nemo-v1-2373-v2 to be ready
Inference service zonemercy-acute-nemo-v1-2373-v2 ready after 221.35930967330933s
Pipeline stage ISVCDeployer completed in 222.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6212158203125s
Received healthy response to inference request in 1.7284855842590332s
Received healthy response to inference request in 1.6959598064422607s
Received healthy response to inference request in 1.7435131072998047s
Received healthy response to inference request in 1.7342987060546875s
5 requests
0 failed requests
5th percentile: 1.7024649620056151
10th percentile: 1.7089701175689698
20th percentile: 1.7219804286956788
30th percentile: 1.7296482086181642
40th percentile: 1.7319734573364258
50th percentile: 1.7342987060546875
60th percentile: 1.7379844665527344
70th percentile: 1.7416702270507813
80th percentile: 1.9190536499023438
90th percentile: 2.270134735107422
95th percentile: 2.445675277709961
99th percentile: 2.586107711791992
mean time: 1.9046946048736573
Pipeline stage StressChecker completed in 10.25s
zonemercy-acute-nemo-v1-_2373_v2 status is now deployed due to DeploymentManager action
zonemercy-acute-nemo-v1-_2373_v2 status is now inactive due to auto deactivation removed underperforming models
zonemercy-acute-nemo-v1-_2373_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics