Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v120-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v120-mkmlizer to finish
neversleep-noromaid-v0-8068-v120-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v120-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
neversleep-noromaid-v0-8068-v120-mkmlizer: Downloaded to shared memory in 122.827s
neversleep-noromaid-v0-8068-v120-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v120-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v120-mkmlizer: quantized model in 120.004s
neversleep-noromaid-v0-8068-v120-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 242.832s
neversleep-noromaid-v0-8068-v120-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v120-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v120-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v120
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v120/special_tokens_map.json
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v120/config.json
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v120/tokenizer_config.json
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v120/tokenizer.model
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v120/tokenizer.json
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v120/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v120/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v120/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v120/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v120-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
neversleep-noromaid-v0-8068-v120-mkmlizer:
Loading 0: 0%| | 0/995 [00:00<?, ?it/s]
Loading 0: 5%|▌ | 52/995 [00:03<01:11, 13.20it/s]
Loading 0: 11%|█ | 107/995 [00:06<00:51, 17.11it/s]
Loading 0: 16%|█▋ | 162/995 [00:11<01:01, 13.47it/s]
Loading 0: 21%|██ | 210/995 [00:18<01:17, 10.12it/s]
Loading 0: 27%|██▋ | 265/995 [00:20<00:55, 13.17it/s]
Loading 0: 28%|██▊ | 277/995 [00:34<00:54, 13.17it/s]
Loading 0: 28%|██▊ | 278/995 [00:42<03:07, 3.83it/s]
Loading 0: 32%|███▏ | 320/995 [00:44<02:03, 5.49it/s]
Loading 0: 37%|███▋ | 368/995 [00:45<01:18, 8.02it/s]
Loading 0: 43%|████▎ | 423/995 [00:46<00:48, 11.69it/s]
Loading 0: 48%|████▊ | 478/995 [00:47<00:32, 16.06it/s]
Loading 0: 53%|█████▎ | 526/995 [00:48<00:23, 19.99it/s]
Loading 0: 57%|█████▋ | 564/995 [01:02<00:21, 19.99it/s]
Loading 0: 57%|█████▋ | 565/995 [01:10<01:19, 5.44it/s]
Loading 0: 58%|█████▊ | 581/995 [01:11<01:10, 5.87it/s]
Loading 0: 64%|██████▍ | 636/995 [01:12<00:39, 9.00it/s]
Loading 0: 69%|██████▉ | 691/995 [01:13<00:23, 12.78it/s]
Loading 0: 74%|███████▍ | 739/995 [01:14<00:15, 16.38it/s]
Loading 0: 80%|███████▉ | 794/995 [01:16<00:09, 20.95it/s]
Loading 0: 85%|████████▍ | 845/995 [01:30<00:07, 20.95it/s]
Loading 0: 85%|████████▌ | 846/995 [01:38<00:24, 5.99it/s]
Loading 0: 85%|████████▌ | 849/995 [01:39<00:25, 5.75it/s]
Loading 0: 90%|█████████ | 897/995 [01:40<00:11, 8.43it/s]
Loading 0: 96%|█████████▌| 952/995 [01:41<00:03, 12.41it/s]
Loading 0: 100%|██████████| 995/995 [01:43<00:00, 15.06it/s]
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v120-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v120-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
neversleep-noromaid-v0-8068-v120-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v120-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v120-mkmlizer: warnings.warn(
Failed to get response for submission blend_pefis_2024-07-04: ('http://neversleep-noromaid-v0-8068-v116-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:55438->127.0.0.1:8080: read: connection reset by peer\n')
neversleep-noromaid-v0-8068-v120-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.63it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.56it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.36it/s]
neversleep-noromaid-v0-8068-v120-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v120-mkmlizer: Saving duration: 2.140s
neversleep-noromaid-v0-8068-v120-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.636s
neversleep-noromaid-v0-8068-v120-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v120-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v120-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v120_reward
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v120_reward/config.json
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v120_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v120_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v120_reward/merges.txt
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v120_reward/vocab.json
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v120_reward/tokenizer.json
neversleep-noromaid-v0-8068-v120-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v120_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v120-mkmlizer completed after 441.86s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v120-mkmlizer
Pipeline stage MKMLizer completed in 442.77s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v120
Waiting for inference service neversleep-noromaid-v0-8068-v120 to be ready
Inference service neversleep-noromaid-v0-8068-v120 ready after 80.38371992111206s
Pipeline stage ISVCDeployer completed in 87.58s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.259235143661499s
Received healthy response to inference request in 2.473013162612915s
Received healthy response to inference request in 2.386601686477661s
Received healthy response to inference request in 2.426582098007202s
Received healthy response to inference request in 2.3778235912323s
5 requests
0 failed requests
5th percentile: 2.379579210281372
10th percentile: 2.381334829330444
20th percentile: 2.384846067428589
30th percentile: 2.3945977687835693
40th percentile: 2.4105899333953857
50th percentile: 2.426582098007202
60th percentile: 2.4451545238494874
70th percentile: 2.4637269496917726
80th percentile: 2.630257558822632
90th percentile: 2.9447463512420655
95th percentile: 3.101990747451782
99th percentile: 3.2277862644195556
mean time: 2.5846511363983153
Pipeline stage StressChecker completed in 13.69s
neversleep-noromaid-v0_8068_v120 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v120 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0_8068_v120
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v120 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.83s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v120/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v120/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v120/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v120/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v120/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v120/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v120/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v120/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v120/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v120_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v120_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v120_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v120_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v120_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v120_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v120_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 9.88s
neversleep-noromaid-v0_8068_v120 status is now torndown due to DeploymentManager action