setiaku-lyra-12b-v1

developer_uid: sao10k
submission_id: setiaku-lyra-12b-v1_v1
model_name: Lyra-1
model_group: Setiaku/Lyra-12B-v1
status: torndown
timestamp: 2024-08-02T16:12:59+00:00
num_battles: 14924
num_wins: 6835
celo_rating: 1194.8
family_friendly_score: 0.0
submission_type: basic
model_repo: Setiaku/Lyra-12B-v1
model_architecture: MistralForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: Lyra-1
is_internal_developer: False
language_model: Setiaku/Lyra-12B-v1
model_size: 13B
ranking_group: single
us_pacific_date: 2024-08-02
win_ratio: 0.45798713481640313
generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.15, 'top_k': 50, 'presence_penalty': 0.15, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', '\nYou:', '</s>', '<|', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64, 'reward_max_token_input': 512}
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}
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name setiaku-lyra-12b-v1-v1-mkmlizer
Waiting for job on setiaku-lyra-12b-v1-v1-mkmlizer to finish
setiaku-lyra-12b-v1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
setiaku-lyra-12b-v1-v1-mkmlizer: ║     _____            __           __                                ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║       /___/                                                         ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║                                                                     ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║  Version: 0.9.9                                                     ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║                                                                     ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║  belonging to:                                                      ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║                                                                     ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
setiaku-lyra-12b-v1-v1-mkmlizer: ║                                                                     ║
setiaku-lyra-12b-v1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-elo-alignment-run-3_v17: ('http://chaiml-elo-alignment-run-3-v17-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:43672->127.0.0.1:8080: read: connection reset by peer\n')
setiaku-lyra-12b-v1-v1-mkmlizer: Downloaded to shared memory in 66.893s
setiaku-lyra-12b-v1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcdluqu01, device:0
setiaku-lyra-12b-v1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
setiaku-lyra-12b-v1-v1-mkmlizer: quantized model in 36.211s
setiaku-lyra-12b-v1-v1-mkmlizer: Processed model Setiaku/Lyra-12B-v1 in 103.104s
setiaku-lyra-12b-v1-v1-mkmlizer: creating bucket guanaco-mkml-models
setiaku-lyra-12b-v1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
setiaku-lyra-12b-v1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/setiaku-lyra-12b-v1-v1
setiaku-lyra-12b-v1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/setiaku-lyra-12b-v1-v1/special_tokens_map.json
setiaku-lyra-12b-v1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/setiaku-lyra-12b-v1-v1/config.json
setiaku-lyra-12b-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/setiaku-lyra-12b-v1-v1/tokenizer_config.json
setiaku-lyra-12b-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/setiaku-lyra-12b-v1-v1/tokenizer.json
setiaku-lyra-12b-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/setiaku-lyra-12b-v1-v1/flywheel_model.0.safetensors
setiaku-lyra-12b-v1-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
setiaku-lyra-12b-v1-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.92it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 48.08it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:10, 31.88it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.59it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:08, 41.14it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 41.61it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:08, 37.05it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:09, 32.31it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:09, 34.48it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:07, 43.23it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:07, 41.70it/s]
Loading 0:  19%|█▉        | 69/363 [00:01<00:07, 41.57it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 44.51it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 34.23it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 37.13it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:07, 35.60it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:07, 34.51it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 36.21it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:07, 35.26it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 36.00it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:05, 41.74it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 41.33it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 40.19it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.33it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 38.56it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:07, 30.40it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 32.48it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 40.47it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:04, 40.58it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 36.19it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:06, 31.62it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.40it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 41.74it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.29it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:03, 43.13it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:03, 41.49it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:04, 37.03it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:04, 36.01it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 34.95it/s]
Loading 0:  60%|██████    | 219/363 [00:05<00:03, 42.13it/s]
Loading 0:  62%|██████▏   | 224/363 [00:05<00:03, 42.11it/s]
Loading 0:  63%|██████▎   | 229/363 [00:06<00:03, 36.35it/s]
Loading 0:  64%|██████▍   | 233/363 [00:06<00:04, 32.29it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 34.24it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:02, 41.77it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 42.37it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 42.97it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 44.46it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 41.35it/s]
Loading 0:  75%|███████▍  | 271/363 [00:07<00:02, 32.66it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 32.23it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 40.28it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 41.67it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:02, 35.20it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:02, 30.93it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 34.02it/s]
Loading 0:  85%|████████▌ | 309/363 [00:08<00:01, 41.55it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 42.59it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 43.15it/s]
Loading 0:  90%|████████▉ | 325/363 [00:08<00:00, 41.46it/s]
Loading 0:  91%|█████████ | 330/363 [00:08<00:00, 36.49it/s]
Loading 0:  92%|█████████▏| 334/363 [00:08<00:00, 35.48it/s]
Loading 0:  93%|█████████▎| 338/363 [00:08<00:00, 34.25it/s]
Loading 0:  95%|█████████▌| 345/363 [00:09<00:00, 42.16it/s]
Loading 0:  96%|█████████▋| 350/363 [00:09<00:00, 42.86it/s]
Loading 0:  98%|█████████▊| 355/363 [00:09<00:00, 37.58it/s]
Loading 0:  99%|█████████▉| 359/363 [00:15<00:01,  2.32it/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.
setiaku-lyra-12b-v1-v1-mkmlizer:   warnings.warn(
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
setiaku-lyra-12b-v1-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.
setiaku-lyra-12b-v1-v1-mkmlizer:   warnings.warn(
setiaku-lyra-12b-v1-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.
setiaku-lyra-12b-v1-v1-mkmlizer:   warnings.warn(
setiaku-lyra-12b-v1-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 [00:09<00:00,  4.74s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.90s/it]
setiaku-lyra-12b-v1-v1-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.48it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  4.06it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.71it/s]
setiaku-lyra-12b-v1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
setiaku-lyra-12b-v1-v1-mkmlizer: Saving duration: 1.353s
setiaku-lyra-12b-v1-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.757s
setiaku-lyra-12b-v1-v1-mkmlizer: creating bucket guanaco-reward-models
setiaku-lyra-12b-v1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
setiaku-lyra-12b-v1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/setiaku-lyra-12b-v1-v1_reward
setiaku-lyra-12b-v1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/setiaku-lyra-12b-v1-v1_reward/config.json
setiaku-lyra-12b-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/setiaku-lyra-12b-v1-v1_reward/tokenizer_config.json
setiaku-lyra-12b-v1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/setiaku-lyra-12b-v1-v1_reward/special_tokens_map.json
setiaku-lyra-12b-v1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/setiaku-lyra-12b-v1-v1_reward/merges.txt
setiaku-lyra-12b-v1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/setiaku-lyra-12b-v1-v1_reward/vocab.json
setiaku-lyra-12b-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/setiaku-lyra-12b-v1-v1_reward/tokenizer.json
setiaku-lyra-12b-v1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/setiaku-lyra-12b-v1-v1_reward/reward.tensors
Job setiaku-lyra-12b-v1-v1-mkmlizer completed after 158.46s with status: succeeded
Stopping job with name setiaku-lyra-12b-v1-v1-mkmlizer
Pipeline stage MKMLizer completed in 159.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service setiaku-lyra-12b-v1-v1
Waiting for inference service setiaku-lyra-12b-v1-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
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 setiaku-lyra-12b-v1-v1 ready after 141.2740068435669s
Pipeline stage ISVCDeployer completed in 142.86s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.713411569595337s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.766174077987671s
Received healthy response to inference request in 1.5865204334259033s
Received healthy response to inference request in 2.1225171089172363s
Received healthy response to inference request in 1.8231348991394043s
5 requests
0 failed requests
5th percentile: 1.622451162338257
10th percentile: 1.6583818912506103
20th percentile: 1.7302433490753173
30th percentile: 1.7775662422180176
40th percentile: 1.8003505706787108
50th percentile: 1.8231348991394043
60th percentile: 1.942887783050537
70th percentile: 2.06264066696167
80th percentile: 2.2406960010528567
90th percentile: 2.4770537853240966
95th percentile: 2.5952326774597165
99th percentile: 2.6897757911682127
mean time: 2.0023516178131104
Pipeline stage StressChecker completed in 10.76s
setiaku-lyra-12b-v1_v1 status is now deployed due to DeploymentManager action
setiaku-lyra-12b-v1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of setiaku-lyra-12b-v1_v1
Running pipeline stage ISVCDeleter
Checking if service setiaku-lyra-12b-v1-v1 is running
Tearing down inference service setiaku-lyra-12b-v1-v1
Service setiaku-lyra-12b-v1-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.58s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key setiaku-lyra-12b-v1-v1/config.json from bucket guanaco-mkml-models
Deleting key setiaku-lyra-12b-v1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key setiaku-lyra-12b-v1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key setiaku-lyra-12b-v1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key setiaku-lyra-12b-v1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key setiaku-lyra-12b-v1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key setiaku-lyra-12b-v1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key setiaku-lyra-12b-v1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key setiaku-lyra-12b-v1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key setiaku-lyra-12b-v1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key setiaku-lyra-12b-v1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key setiaku-lyra-12b-v1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.11s
setiaku-lyra-12b-v1_v1 status is now torndown due to DeploymentManager action