Running pipeline stage MKMLizer
Starting job with name cycy233-l3-ba-e-v6-c2-v2-mkmlizer
Waiting for job on cycy233-l3-ba-e-v6-c2-v2-mkmlizer to finish
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ /___/ ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ Version: 0.9.7 ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ║ ║
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: Downloaded to shared memory in 21.880s
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_8ptlux3, device:0
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: quantized model in 25.958s
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: Processed model cycy233/L3-ba-e-v6-c2 in 47.838s
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ba-e-v6-c2-v2
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v6-c2-v2/config.json
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v6-c2-v2/special_tokens_map.json
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v6-c2-v2/tokenizer_config.json
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v6-c2-v2/tokenizer.json
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ba-e-v6-c2-v2/flywheel_model.0.safetensors
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-ba-e-v6-c2-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:07, 36.36it/s]
Loading 0: 5%|▍ | 14/291 [00:00<00:05, 48.89it/s]
Loading 0: 8%|▊ | 23/291 [00:00<00:05, 52.48it/s]
Loading 0: 11%|█ | 32/291 [00:00<00:04, 54.31it/s]
Loading 0: 14%|█▍ | 41/291 [00:00<00:04, 54.91it/s]
Loading 0: 17%|█▋ | 50/291 [00:00<00:04, 54.45it/s]
Loading 0: 20%|██ | 59/291 [00:01<00:04, 53.80it/s]
Loading 0: 23%|██▎ | 67/291 [00:01<00:03, 59.42it/s]
Loading 0: 25%|██▌ | 74/291 [00:01<00:03, 56.56it/s]
Loading 0: 27%|██▋ | 80/291 [00:01<00:03, 54.80it/s]
Loading 0: 30%|██▉ | 86/291 [00:01<00:05, 35.26it/s]
Loading 0: 32%|███▏ | 94/291 [00:01<00:04, 42.71it/s]
Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 43.10it/s]
Loading 0: 36%|███▋ | 106/291 [00:02<00:04, 45.17it/s]
Loading 0: 39%|███▉ | 113/291 [00:02<00:04, 42.45it/s]
Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 49.54it/s]
Loading 0: 44%|████▎ | 127/291 [00:02<00:03, 47.67it/s]
Loading 0: 46%|████▌ | 133/291 [00:02<00:03, 48.67it/s]
Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 51.25it/s]
Loading 0: 50%|████▉ | 145/291 [00:02<00:03, 47.97it/s]
Loading 0: 52%|█████▏ | 151/291 [00:03<00:02, 47.88it/s]
Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 50.26it/s]
Loading 0: 56%|█████▌ | 163/291 [00:03<00:02, 46.93it/s]
Loading 0: 58%|█████▊ | 168/291 [00:03<00:02, 45.63it/s]
Loading 0: 60%|██████ | 175/291 [00:03<00:02, 51.72it/s]
Loading 0: 62%|██████▏ | 181/291 [00:03<00:02, 44.77it/s]
Loading 0: 64%|██████▍ | 187/291 [00:03<00:02, 37.04it/s]
Loading 0: 66%|██████▌ | 192/291 [00:04<00:02, 37.98it/s]
Loading 0: 68%|██████▊ | 198/291 [00:04<00:02, 42.42it/s]
Loading 0: 70%|██████▉ | 203/291 [00:04<00:02, 36.51it/s]
Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 44.58it/s]
Loading 0: 75%|███████▍ | 217/291 [00:04<00:01, 44.19it/s]
Loading 0: 76%|███████▋ | 222/291 [00:04<00:01, 44.54it/s]
Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 49.63it/s]
Loading 0: 81%|████████ | 235/291 [00:05<00:01, 46.07it/s]
Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 45.59it/s]
Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 50.46it/s]
Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 47.77it/s]
Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 45.69it/s]
Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 50.56it/s]
Loading 0: 93%|█████████▎| 271/291 [00:05<00:00, 46.98it/s]
Loading 0: 95%|█████████▍| 276/291 [00:05<00:00, 45.64it/s]
Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 42.88it/s]
Loading 0: 99%|█████████▊| 287/291 [00:11<00:01, 3.29it/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.
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: warnings.warn(
cycy233-l3-ba-e-v6-c2-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.
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: warnings.warn(
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: Saving duration: 1.372s
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.729s
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ba-e-v6-c2-v2_reward
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ba-e-v6-c2-v2_reward/config.json
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ba-e-v6-c2-v2_reward/special_tokens_map.json
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ba-e-v6-c2-v2_reward/tokenizer_config.json
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ba-e-v6-c2-v2_reward/merges.txt
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ba-e-v6-c2-v2_reward/vocab.json
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ba-e-v6-c2-v2_reward/tokenizer.json
cycy233-l3-ba-e-v6-c2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ba-e-v6-c2-v2_reward/reward.tensors
Job cycy233-l3-ba-e-v6-c2-v2-mkmlizer completed after 84.82s with status: succeeded
Stopping job with name cycy233-l3-ba-e-v6-c2-v2-mkmlizer
Pipeline stage MKMLizer completed in 85.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ba-e-v6-c2-v2
Waiting for inference service cycy233-l3-ba-e-v6-c2-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cycy233-l3-ba-e-v6-c2-v2 ready after 90.79699945449829s
Pipeline stage ISVCDeployer completed in 92.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.300966501235962s
Received healthy response to inference request in 1.4946987628936768s
Received healthy response to inference request in 1.469794511795044s
Received healthy response to inference request in 1.435305118560791s
Received healthy response to inference request in 1.5215537548065186s
5 requests
0 failed requests
5th percentile: 1.4422029972076416
10th percentile: 1.449100875854492
20th percentile: 1.4628966331481934
30th percentile: 1.4747753620147706
40th percentile: 1.4847370624542235
50th percentile: 1.4946987628936768
60th percentile: 1.5054407596588135
70th percentile: 1.5161827564239503
80th percentile: 1.6774363040924074
90th percentile: 1.9892014026641847
95th percentile: 2.145083951950073
99th percentile: 2.2697899913787842
mean time: 1.6444637298583984
Pipeline stage StressChecker completed in 8.91s
cycy233-l3-ba-e-v6-c2_v2 status is now deployed due to DeploymentManager action
Failed to get response for submission blend_kobem_2024-07-23: ('http://undi95-meta-llama-3-70b-6209-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:42120->127.0.0.1:8080: read: connection reset by peer\n')
cycy233-l3-ba-e-v6-c2_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-ba-e-v6-c2_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-ba-e-v6-c2-v2 is running
Tearing down inference service cycy233-l3-ba-e-v6-c2-v2
Service cycy233-l3-ba-e-v6-c2-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.99s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-ba-e-v6-c2-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v6-c2-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v6-c2-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v6-c2-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v6-c2-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-ba-e-v6-c2-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v6-c2-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v6-c2-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v6-c2-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v6-c2-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v6-c2-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v6-c2-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.54s
cycy233-l3-ba-e-v6-c2_v2 status is now torndown due to DeploymentManager action