Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v136-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v136-mkmlizer to finish
neversleep-noromaid-v0-8068-v136-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ Version: 0.9.5.post2 ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v136-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
neversleep-noromaid-v0-8068-v136-mkmlizer: Downloaded to shared memory in 105.984s
neversleep-noromaid-v0-8068-v136-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v136-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
neversleep-noromaid-v0-8068-v136-mkmlizer: quantized model in 80.850s
neversleep-noromaid-v0-8068-v136-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 186.834s
neversleep-noromaid-v0-8068-v136-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v136-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v136-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v136
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v136/config.json
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v136/tokenizer_config.json
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v136/tokenizer.json
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v136/special_tokens_map.json
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v136/tokenizer.model
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v136/flywheel_model.5.safetensors
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v136/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v136/flywheel_model.4.safetensors
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v136/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v136/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v136/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v136-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
neversleep-noromaid-v0-8068-v136-mkmlizer:
Loading 0: 0%| | 0/995 [00:00<?, ?it/s]
Loading 0: 5%|▌ | 52/995 [00:01<00:18, 50.29it/s]
Loading 0: 11%|█ | 107/995 [00:02<00:16, 52.99it/s]
Loading 0: 16%|█▋ | 162/995 [00:03<00:15, 53.20it/s]
Loading 0: 18%|█▊ | 181/995 [00:14<00:15, 53.20it/s]
Loading 0: 18%|█▊ | 182/995 [00:14<01:39, 8.16it/s]
Loading 0: 21%|██ | 210/995 [00:15<01:18, 10.04it/s]
Loading 0: 27%|██▋ | 265/995 [00:16<00:46, 15.69it/s]
Loading 0: 32%|███▏ | 320/995 [00:17<00:30, 21.90it/s]
Loading 0: 36%|███▌ | 356/995 [00:27<01:09, 9.25it/s]
Loading 0: 37%|███▋ | 368/995 [00:28<01:06, 9.42it/s]
Loading 0: 43%|████▎ | 423/995 [00:29<00:39, 14.57it/s]
Loading 0: 48%|████▊ | 478/995 [00:30<00:25, 20.39it/s]
Loading 0: 52%|█████▏ | 522/995 [00:40<00:23, 20.39it/s]
Loading 0: 53%|█████▎ | 523/995 [00:40<00:48, 9.73it/s]
Loading 0: 53%|█████▎ | 526/995 [00:41<00:51, 9.09it/s]
Loading 0: 58%|█████▊ | 581/995 [00:42<00:29, 14.21it/s]
Loading 0: 64%|██████▍ | 636/995 [00:43<00:17, 20.01it/s]
Loading 0: 69%|██████▉ | 691/995 [00:44<00:11, 26.14it/s]
Loading 0: 70%|██████▉ | 696/995 [00:54<00:11, 26.14it/s]
Loading 0: 70%|███████ | 697/995 [00:54<00:36, 8.09it/s]
Loading 0: 74%|███████▍ | 739/995 [00:55<00:22, 11.14it/s]
Loading 0: 80%|███████▉ | 794/995 [00:56<00:12, 16.29it/s]
Loading 0: 85%|████████▌ | 849/995 [00:57<00:06, 22.03it/s]
Loading 0: 87%|████████▋ | 863/995 [01:07<00:05, 22.03it/s]
Loading 0: 87%|████████▋ | 864/995 [01:07<00:15, 8.19it/s]
Loading 0: 90%|█████████ | 897/995 [01:08<00:09, 10.35it/s]
Loading 0: 96%|█████████▌| 952/995 [01:09<00:02, 15.69it/s]
Loading 0: 100%|██████████| 995/995 [01:10<00:00, 18.66it/s]
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v136-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v136-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v136-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v136-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-noromaid-v0-8068-v136-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v136-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.98it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.25it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.97it/s]
neversleep-noromaid-v0-8068-v136-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v136-mkmlizer: Saving duration: 1.788s
neversleep-noromaid-v0-8068-v136-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 11.461s
neversleep-noromaid-v0-8068-v136-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v136-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v136-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v136_reward
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v136_reward/config.json
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v136_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v136_reward/vocab.json
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v136_reward/merges.txt
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v136_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v136_reward/tokenizer.json
neversleep-noromaid-v0-8068-v136-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v136_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v136-mkmlizer completed after 241.0s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v136-mkmlizer
Pipeline stage MKMLizer completed in 241.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v136
Waiting for inference service neversleep-noromaid-v0-8068-v136 to be ready
Inference service neversleep-noromaid-v0-8068-v136 ready after 90.44665551185608s
Pipeline stage ISVCDeployer completed in 97.39s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.321117639541626s
Received healthy response to inference request in 2.249349594116211s
Received healthy response to inference request in 2.3051984310150146s
Received healthy response to inference request in 2.1184146404266357s
Received healthy response to inference request in 2.297544479370117s
5 requests
0 failed requests
5th percentile: 2.1446016311645506
10th percentile: 2.170788621902466
20th percentile: 2.223162603378296
30th percentile: 2.2589885711669924
40th percentile: 2.2782665252685548
50th percentile: 2.297544479370117
60th percentile: 2.300606060028076
70th percentile: 2.3036676406860352
80th percentile: 2.508382272720337
90th percentile: 2.9147499561309815
95th percentile: 3.1179337978363035
99th percentile: 3.2804808712005613
mean time: 2.4583249568939207
Pipeline stage StressChecker completed in 13.04s
neversleep-noromaid-v0_8068_v136 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v136 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0_8068_v136
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v136 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.94s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v136/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v136/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v136/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v136/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v136/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v136/flywheel_model.4.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v136/flywheel_model.5.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v136/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v136/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v136/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v136/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v136_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v136_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v136_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v136_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v136_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v136_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v136_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 8.91s
neversleep-noromaid-v0_8068_v136 status is now torndown due to DeploymentManager action