Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v123-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v123-mkmlizer to finish
neversleep-noromaid-v0-8068-v123-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
neversleep-noromaid-v0-8068-v123-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v123-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
neversleep-noromaid-v0-8068-v123-mkmlizer: Downloaded to shared memory in 140.364s
neversleep-noromaid-v0-8068-v123-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v123-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission neversleep-noromaid-v0_8068_v121: ('http://neversleep-noromaid-v0-8068-v121-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:54910->127.0.0.1:8080: read: connection reset by peer\n')
neversleep-noromaid-v0-8068-v123-mkmlizer: quantized model in 102.109s
neversleep-noromaid-v0-8068-v123-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 242.473s
neversleep-noromaid-v0-8068-v123-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v123-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v123-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v123
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v123/config.json
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v123/tokenizer_config.json
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v123/special_tokens_map.json
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v123/tokenizer.json
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v123/tokenizer.model
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v123/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v123/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v123/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v123/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v123-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-v123-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v123-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v123-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v123-mkmlizer:
Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]
Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.41s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.43s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.87s/it]
neversleep-noromaid-v0-8068-v123-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.65it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.71it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.47it/s]
neversleep-noromaid-v0-8068-v123-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v123-mkmlizer: Saving duration: 2.178s
neversleep-noromaid-v0-8068-v123-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.822s
neversleep-noromaid-v0-8068-v123-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v123-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v123-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v123_reward
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v123_reward/config.json
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v123_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v123_reward/merges.txt
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v123_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v123_reward/vocab.json
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v123_reward/tokenizer.json
neversleep-noromaid-v0-8068-v123-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v123_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v123-mkmlizer completed after 314.05s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v123-mkmlizer
Pipeline stage MKMLizer completed in 315.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v123
Waiting for inference service neversleep-noromaid-v0-8068-v123 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service neversleep-noromaid-v0-8068-v123 ready after 81.24641871452332s
Pipeline stage ISVCDeployer completed in 88.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1262893676757812s
Received healthy response to inference request in 2.580260753631592s
Received healthy response to inference request in 1.7617769241333008s
Received healthy response to inference request in 2.3109991550445557s
Received healthy response to inference request in 2.227987289428711s
5 requests
0 failed requests
5th percentile: 1.8550189971923827
10th percentile: 1.9482610702514649
20th percentile: 2.134745216369629
30th percentile: 2.24458966255188
40th percentile: 2.2777944087982176
50th percentile: 2.3109991550445557
60th percentile: 2.41870379447937
70th percentile: 2.5264084339141846
80th percentile: 2.6894664764404297
90th percentile: 2.9078779220581055
95th percentile: 3.0170836448669434
99th percentile: 3.1044482231140136
mean time: 2.401462697982788
Pipeline stage StressChecker completed in 12.69s
neversleep-noromaid-v0_8068_v123 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v123 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0_8068_v123
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v123 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.86s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v123/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v123/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v123/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v123/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v123/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v123/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v123/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v123/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v123/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v123_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v123_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v123_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v123_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v123_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v123_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v123_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 9.63s
neversleep-noromaid-v0_8068_v123 status is now torndown due to DeploymentManager action