Running pipeline stage MKMLizer
Starting job with name cycy233-l3-ss-v1-c3-v3-mkmlizer
Waiting for job on cycy233-l3-ss-v1-c3-v3-mkmlizer to finish
cycy233-l3-ss-v1-c3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ _____ __ __ ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ /___/ ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ Version: 0.9.9 ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ belonging to: ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ║ ║
cycy233-l3-ss-v1-c3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ss-v1-c3-v3-mkmlizer: Downloaded to shared memory in 25.383s
cycy233-l3-ss-v1-c3-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphtpidry6, device:0
cycy233-l3-ss-v1-c3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ss-v1-c3-v3-mkmlizer: quantized model in 26.128s
cycy233-l3-ss-v1-c3-v3-mkmlizer: Processed model cycy233/L3-ss-v1-c3 in 51.511s
cycy233-l3-ss-v1-c3-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ss-v1-c3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ss-v1-c3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ss-v1-c3-v3
cycy233-l3-ss-v1-c3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ss-v1-c3-v3/config.json
cycy233-l3-ss-v1-c3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ss-v1-c3-v3/special_tokens_map.json
cycy233-l3-ss-v1-c3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ss-v1-c3-v3/tokenizer_config.json
cycy233-l3-ss-v1-c3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ss-v1-c3-v3/tokenizer.json
cycy233-l3-ss-v1-c3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ss-v1-c3-v3/flywheel_model.0.safetensors
cycy233-l3-ss-v1-c3-v3-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.
cycy233-l3-ss-v1-c3-v3-mkmlizer: warnings.warn(
cycy233-l3-ss-v1-c3-v3-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-ss-v1-c3-v3-mkmlizer: warnings.warn(
cycy233-l3-ss-v1-c3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ss-v1-c3-v3-mkmlizer: Saving duration: 1.355s
cycy233-l3-ss-v1-c3-v3-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.211s
cycy233-l3-ss-v1-c3-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ss-v1-c3-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ss-v1-c3-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ss-v1-c3-v3_reward
cycy233-l3-ss-v1-c3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ss-v1-c3-v3_reward/config.json
cycy233-l3-ss-v1-c3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ss-v1-c3-v3_reward/special_tokens_map.json
cycy233-l3-ss-v1-c3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ss-v1-c3-v3_reward/tokenizer_config.json
cycy233-l3-ss-v1-c3-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ss-v1-c3-v3_reward/vocab.json
cycy233-l3-ss-v1-c3-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ss-v1-c3-v3_reward/merges.txt
cycy233-l3-ss-v1-c3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ss-v1-c3-v3_reward/tokenizer.json
cycy233-l3-ss-v1-c3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ss-v1-c3-v3_reward/reward.tensors
Job cycy233-l3-ss-v1-c3-v3-mkmlizer completed after 101.81s with status: succeeded
Stopping job with name cycy233-l3-ss-v1-c3-v3-mkmlizer
Pipeline stage MKMLizer completed in 102.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ss-v1-c3-v3
Waiting for inference service cycy233-l3-ss-v1-c3-v3 to be ready
Failed to get response for submission trace2333-fd-llama3-v1-f_9760_v1: ('http://trace2333-fd-llama3-v1-f-9760-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:39354->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission trace2333-fd-llama3-v1-f_9760_v1: ('http://trace2333-fd-llama3-v1-f-9760-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Inference service cycy233-l3-ss-v1-c3-v3 ready after 290.2352159023285s
Pipeline stage ISVCDeployer completed in 292.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2706518173217773s
Received healthy response to inference request in 1.4998559951782227s
Received healthy response to inference request in 1.4381718635559082s
Received healthy response to inference request in 1.4603197574615479s
Received healthy response to inference request in 1.5585243701934814s
5 requests
0 failed requests
5th percentile: 1.4426014423370361
10th percentile: 1.447031021118164
20th percentile: 1.45589017868042
30th percentile: 1.468227005004883
40th percentile: 1.4840415000915528
50th percentile: 1.4998559951782227
60th percentile: 1.5233233451843262
70th percentile: 1.5467906951904298
80th percentile: 1.7009498596191408
90th percentile: 1.985800838470459
95th percentile: 2.128226327896118
99th percentile: 2.2421667194366455
mean time: 1.6455047607421875
Pipeline stage StressChecker completed in 8.88s
cycy233-l3-ss-v1-c3_v3 status is now deployed due to DeploymentManager action
cycy233-l3-ss-v1-c3_v3 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-ss-v1-c3_v3 status is now torndown due to DeploymentManager action