submission_id: sao10k-mn-12b-lyra-v2a1_v2
developer_uid: sao10k
alignment_samples: 12411
alignment_score: 0.28277541586517563
best_of: 8
celo_rating: 1243.18
display_name: Lyra-v2a1
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', '<', '<|', '\n\n', '[/INST]'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: Sao10K/MN-12B-Lyra-v2a1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Sao10K/MN-12B-Lyra-v2a1
model_name: Lyra-v2a1
model_num_parameters: 12772070400.0
model_repo: Sao10K/MN-12B-Lyra-v2a1
model_size: 13B
num_battles: 12411
num_wins: 6559
propriety_score: 0.7426655490360435
propriety_total_count: 1193.0
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: 2024-08-12T12:45:55+00:00
us_pacific_date: 2024-08-12
win_ratio: 0.5284827975183305
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-mn-12b-lyra-v2a1-v2-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v2a1-v2-mkmlizer to finish
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ _____ __ __ ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ /___/ ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ Version: 0.9.9 ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ https://mk1.ai ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ belonging to: ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ Chai Research Corp. ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: Downloaded to shared memory in 30.199s
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgc8v82ki, device:0
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: quantized model in 35.335s
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: Processed model Sao10K/MN-12B-Lyra-v2a1 in 65.535s
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v2
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v2/config.json
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v2/special_tokens_map.json
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v2/tokenizer_config.json
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v2/tokenizer.json
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v2/flywheel_model.0.safetensors
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:04, 3.00s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:47, 1.24it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:42, 3.42it/s] Loading 0: 6%|▌ | 20/363 [00:06<00:55, 6.19it/s] Loading 0: 7%|▋ | 25/363 [00:06<00:39, 8.63it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:25, 13.18it/s] Loading 0: 10%|█ | 38/363 [00:06<00:19, 16.95it/s] Loading 0: 12%|█▏ | 43/363 [00:06<00:15, 20.63it/s] Loading 0: 14%|█▍ | 50/363 [00:06<00:11, 27.25it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:09, 31.18it/s] Loading 0: 17%|█▋ | 62/363 [00:07<00:11, 26.16it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:09, 31.36it/s] Loading 0: 20%|██ | 74/363 [00:07<00:08, 34.09it/s] Loading 0: 22%|██▏ | 79/363 [00:07<00:08, 34.46it/s] Loading 0: 24%|██▎ | 86/363 [00:07<00:06, 40.03it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:06, 41.27it/s] Loading 0: 27%|██▋ | 97/363 [00:08<00:06, 41.71it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 47.10it/s] Loading 0: 30%|███ | 110/363 [00:08<00:05, 45.47it/s] Loading 0: 32%|███▏ | 115/363 [00:08<00:05, 44.33it/s] Loading 0: 34%|███▎ | 122/363 [00:08<00:04, 49.07it/s] Loading 0: 35%|███▌ | 128/363 [00:08<00:05, 45.72it/s] Loading 0: 37%|███▋ | 133/363 [00:08<00:05, 43.60it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:04, 48.47it/s] Loading 0: 40%|████ | 146/363 [00:09<00:04, 47.77it/s] Loading 0: 42%|████▏ | 151/363 [00:09<00:04, 45.41it/s] Loading 0: 43%|████▎ | 157/363 [00:09<00:06, 33.95it/s] Loading 0: 44%|████▍ | 161/363 [00:09<00:05, 34.53it/s] Loading 0: 46%|████▌ | 167/363 [00:09<00:05, 38.89it/s] Loading 0: 48%|████▊ | 173/363 [00:09<00:04, 40.01it/s] Loading 0: 49%|████▉ | 178/363 [00:10<00:04, 38.51it/s] Loading 0: 51%|█████ | 184/363 [00:10<00:04, 41.91it/s] Loading 0: 52%|█████▏ | 189/363 [00:10<00:04, 42.99it/s] Loading 0: 53%|█████▎ | 194/363 [00:10<00:03, 44.19it/s] Loading 0: 55%|█████▌ | 200/363 [00:10<00:03, 43.58it/s] Loading 0: 56%|█████▋ | 205/363 [00:10<00:03, 42.04it/s] Loading 0: 58%|█████▊ | 212/363 [00:10<00:03, 47.12it/s] Loading 0: 60%|██████ | 218/363 [00:10<00:03, 44.68it/s] Loading 0: 61%|██████▏ | 223/363 [00:11<00:03, 42.50it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:02, 47.04it/s] Loading 0: 65%|██████▌ | 236/363 [00:11<00:02, 45.65it/s] Loading 0: 66%|██████▋ | 241/363 [00:11<00:02, 44.16it/s] Loading 0: 68%|██████▊ | 247/363 [00:11<00:02, 47.46it/s] Loading 0: 69%|██████▉ | 252/363 [00:11<00:02, 47.07it/s] Loading 0: 71%|███████ | 257/363 [00:11<00:03, 31.95it/s] Loading 0: 72%|███████▏ | 262/363 [00:12<00:02, 35.56it/s] Loading 0: 74%|███████▎ | 267/363 [00:12<00:02, 33.50it/s] Loading 0: 75%|███████▌ | 274/363 [00:12<00:02, 40.92it/s] Loading 0: 77%|███████▋ | 279/363 [00:12<00:02, 41.30it/s] Loading 0: 78%|███████▊ | 284/363 [00:12<00:01, 43.07it/s] Loading 0: 80%|███████▉ | 290/363 [00:12<00:01, 43.00it/s] Loading 0: 81%|████████▏ | 295/363 [00:12<00:01, 42.32it/s] Loading 0: 83%|████████▎ | 302/363 [00:12<00:01, 47.55it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:01, 46.36it/s] Loading 0: 86%|████████▌ | 313/363 [00:13<00:01, 44.46it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:00, 48.92it/s] Loading 0: 90%|████████▉ | 326/363 [00:13<00:00, 46.91it/s] Loading 0: 91%|█████████ | 331/363 [00:13<00:00, 44.14it/s] Loading 0: 93%|█████████▎| 338/363 [00:13<00:00, 48.65it/s] Loading 0: 95%|█████████▍| 344/363 [00:13<00:00, 47.12it/s] Loading 0: 96%|█████████▌| 349/363 [00:13<00:00, 45.22it/s] Loading 0: 98%|█████████▊| 355/363 [00:14<00:00, 33.69it/s] Loading 0: 99%|█████████▉| 359/363 [00:14<00:00, 34.17it/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-mn-12b-lyra-v2a1-v2-mkmlizer: warnings.warn(
sao10k-mn-12b-lyra-v2a1-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-mn-12b-lyra-v2a1-v2-mkmlizer: warnings.warn(
sao10k-mn-12b-lyra-v2a1-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-mn-12b-lyra-v2a1-v2-mkmlizer: warnings.warn(
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.54s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.91s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.16s/it]
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.42it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.92it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.59it/s]
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: Saving duration: 1.344s
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.237s
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: creating bucket guanaco-reward-models
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-mn-12b-lyra-v2a1-v2_reward
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-mn-12b-lyra-v2a1-v2_reward/config.json
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-mn-12b-lyra-v2a1-v2_reward/special_tokens_map.json
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-mn-12b-lyra-v2a1-v2_reward/tokenizer_config.json
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-mn-12b-lyra-v2a1-v2_reward/merges.txt
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-mn-12b-lyra-v2a1-v2_reward/vocab.json
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-mn-12b-lyra-v2a1-v2_reward/tokenizer.json
sao10k-mn-12b-lyra-v2a1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-mn-12b-lyra-v2a1-v2_reward/reward.tensors
Job sao10k-mn-12b-lyra-v2a1-v2-mkmlizer completed after 115.27s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v2a1-v2-mkmlizer
Pipeline stage MKMLizer completed in 116.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-mn-12b-lyra-v2a1-v2
Waiting for inference service sao10k-mn-12b-lyra-v2a1-v2 to be ready
Failed to get response for submission mistralai-mistral-nemo-_9330_v29: ('http://mistralai-mistral-nemo-9330-v29-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:46482->127.0.0.1:8080: read: connection reset by peer\n')
Inference service sao10k-mn-12b-lyra-v2a1-v2 ready after 201.32265639305115s
Pipeline stage ISVCDeployer completed in 203.46s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.470546007156372s
Received healthy response to inference request in 1.6748459339141846s
Received healthy response to inference request in 1.7202107906341553s
Received healthy response to inference request in 1.659064769744873s
Received healthy response to inference request in 1.57804274559021s
5 requests
0 failed requests
5th percentile: 1.5942471504211426
10th percentile: 1.6104515552520753
20th percentile: 1.6428603649139404
30th percentile: 1.6622210025787354
40th percentile: 1.6685334682464599
50th percentile: 1.6748459339141846
60th percentile: 1.6929918766021728
70th percentile: 1.7111378192901612
80th percentile: 1.8702778339385988
90th percentile: 2.1704119205474854
95th percentile: 2.3204789638519285
99th percentile: 2.4405325984954835
mean time: 1.820542049407959
Pipeline stage StressChecker completed in 9.91s
sao10k-mn-12b-lyra-v2a1_v2 status is now deployed due to DeploymentManager action
sao10k-mn-12b-lyra-v2a1_v2 status is now inactive due to auto deactivation removed underperforming models
sao10k-mn-12b-lyra-v2a1_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics