submission_id: neversleep-lumimaid-v0-2-12b_v5
developer_uid: Azazelle
alignment_samples: 0
best_of: 8
celo_rating: 1214.92
display_name: Lumimaid-v0_2-12B-ChatML
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': False}
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<', '<|'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: NeverSleep/Lumimaid-v0.2-12B
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: NeverSleep/Lumimaid-v0.2
model_name: Lumimaid-v0_2-12B-ChatML
model_num_parameters: 12772080640.0
model_repo: NeverSleep/Lumimaid-v0.2-12B
model_size: 13B
num_battles: 13184
num_wins: 6473
propriety_score: 0.7130872483221476
propriety_total_count: 1192.0
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: 2024-08-06T21:59:32+00:00
us_pacific_date: 2024-08-06
win_ratio: 0.4909739077669903
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-lumimaid-v0-2-12b-v5-mkmlizer
Waiting for job on neversleep-lumimaid-v0-2-12b-v5-mkmlizer to finish
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ _____ __ __ ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ /___/ ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ Version: 0.9.9 ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ https://mk1.ai ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ belonging to: ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ Chai Research Corp. ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ║ ║
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: Downloaded to shared memory in 45.547s
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppql0h_g6, device:0
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission zonemercy-lexical-nemo-_1518_v10: ('http://zonemercy-lexical-nemo-1518-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:37018->127.0.0.1:8080: read: connection reset by peer\n')
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: quantized model in 36.635s
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: Processed model NeverSleep/Lumimaid-v0.2-12B in 82.182s
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: creating bucket guanaco-mkml-models
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-lumimaid-v0-2-12b-v5
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-lumimaid-v0-2-12b-v5/special_tokens_map.json
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-lumimaid-v0-2-12b-v5/config.json
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-lumimaid-v0-2-12b-v5/tokenizer_config.json
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-lumimaid-v0-2-12b-v5/tokenizer.json
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-lumimaid-v0-2-12b-v5/flywheel_model.0.safetensors
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:10, 32.56it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 51.80it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 46.36it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 44.29it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 50.09it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 46.53it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.13it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.02it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.41it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:06, 47.26it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 30.34it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 36.90it/s] Loading 0: 21%|██ | 77/363 [00:01<00:07, 39.66it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:08, 34.89it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 42.71it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 41.56it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 40.83it/s] Loading 0: 29%|██▉ | 107/363 [00:02<00:05, 45.17it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 46.04it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 44.08it/s] Loading 0: 34%|███▍ | 123/363 [00:02<00:05, 41.82it/s] Loading 0: 35%|███▌ | 128/363 [00:03<00:05, 40.89it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 44.69it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 44.62it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:07, 27.99it/s] Loading 0: 41%|████ | 149/363 [00:03<00:07, 29.70it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 37.11it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 38.78it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:04, 40.40it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 38.91it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 39.13it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 44.08it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 43.70it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 44.58it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 45.47it/s] Loading 0: 56%|█████▌ | 203/363 [00:04<00:04, 36.94it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 44.27it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 44.38it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:02, 47.88it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 31.19it/s] Loading 0: 64%|██████▍ | 232/363 [00:05<00:04, 32.14it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 35.43it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 36.88it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 38.00it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 40.66it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:02, 35.43it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 43.35it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 43.35it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:02, 44.31it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 42.52it/s] Loading 0: 79%|███████▊ | 285/363 [00:07<00:01, 41.92it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 45.61it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 43.08it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 44.33it/s] Loading 0: 84%|████████▍ | 306/363 [00:14<00:23, 2.41it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:17, 3.11it/s] Loading 0: 86%|████████▌ | 313/363 [00:14<00:13, 3.83it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.22it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 8.65it/s] Loading 0: 91%|█████████ | 330/363 [00:14<00:03, 10.50it/s] Loading 0: 93%|█████████▎| 337/363 [00:15<00:01, 15.41it/s] Loading 0: 94%|█████████▍| 342/363 [00:15<00:01, 18.55it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 22.10it/s] Loading 0: 97%|█████████▋| 352/363 [00:15<00:00, 26.22it/s] Loading 0: 98%|█████████▊| 357/363 [00:15<00:00, 26.52it/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.
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: warnings.warn(
neversleep-lumimaid-v0-2-12b-v5-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.
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: warnings.warn(
neversleep-lumimaid-v0-2-12b-v5-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.
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: warnings.warn(
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.52s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.15s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.35s/it]
neversleep-lumimaid-v0-2-12b-v5-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, 3.91it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.56it/s]
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: Saving duration: 1.319s
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.864s
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: creating bucket guanaco-reward-models
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-lumimaid-v0-2-12b-v5_reward
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-lumimaid-v0-2-12b-v5_reward/merges.txt
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-lumimaid-v0-2-12b-v5_reward/vocab.json
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-lumimaid-v0-2-12b-v5_reward/tokenizer.json
neversleep-lumimaid-v0-2-12b-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-lumimaid-v0-2-12b-v5_reward/reward.tensors
Job neversleep-lumimaid-v0-2-12b-v5-mkmlizer completed after 126.23s with status: succeeded
Stopping job with name neversleep-lumimaid-v0-2-12b-v5-mkmlizer
Pipeline stage MKMLizer completed in 127.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-lumimaid-v0-2-12b-v5
Waiting for inference service neversleep-lumimaid-v0-2-12b-v5 to be ready
Failed to get response for submission zonemercy-lexical-nemo-_1518_v10: ('http://zonemercy-lexical-nemo-1518-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission zonemercy-lexical-nemo-_1518_v10: ('http://zonemercy-lexical-nemo-1518-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission zonemercy-lexical-nemo-_1518_v10: ('http://zonemercy-lexical-nemo-1518-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v97: ('http://mistralai-mixtral-8x7b-3473-v97-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:46602->127.0.0.1:8080: read: connection reset by peer\n')
Inference service neversleep-lumimaid-v0-2-12b-v5 ready after 191.19167494773865s
Pipeline stage ISVCDeployer completed in 193.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.438325881958008s
Received healthy response to inference request in 1.5815093517303467s
Received healthy response to inference request in 1.5812454223632812s
Received healthy response to inference request in 1.5895841121673584s
Received healthy response to inference request in 1.5976171493530273s
5 requests
0 failed requests
5th percentile: 1.5812982082366944
10th percentile: 1.5813509941101074
20th percentile: 1.5814565658569335
30th percentile: 1.583124303817749
40th percentile: 1.5863542079925537
50th percentile: 1.5895841121673584
60th percentile: 1.592797327041626
70th percentile: 1.5960105419158936
80th percentile: 1.7657588958740236
90th percentile: 2.102042388916016
95th percentile: 2.2701841354370114
99th percentile: 2.4046975326538087
mean time: 1.7576563835144043
Pipeline stage StressChecker completed in 9.52s
neversleep-lumimaid-v0-2-12b_v5 status is now deployed due to DeploymentManager action
neversleep-lumimaid-v0-2-12b_v5 status is now inactive due to auto deactivation removed underperforming models
neversleep-lumimaid-v0-2-12b_v5 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics