Running pipeline stage MKMLizer
Starting job with name cycy233-l3-s-v0-c4-v1-mkmlizer
Waiting for job on cycy233-l3-s-v0-c4-v1-mkmlizer to finish
Stopping job with name cycy233-l3-s-v0-c4-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-l3-s-v0-c4-v1-mkmlizer
Waiting for job on cycy233-l3-s-v0-c4-v1-mkmlizer to finish
cycy233-l3-s-v0-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ /___/ ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ Version: 0.9.9 ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-s-v0-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-s-v0-c4-v1-mkmlizer: Downloaded to shared memory in 34.499s
cycy233-l3-s-v0-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9mk6z1z4, device:0
cycy233-l3-s-v0-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-s-v0-c4-v1-mkmlizer: quantized model in 26.151s
cycy233-l3-s-v0-c4-v1-mkmlizer: Processed model cycy233/L3-s-v0-c4 in 60.651s
cycy233-l3-s-v0-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-s-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-s-v0-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-s-v0-c4-v1
cycy233-l3-s-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-s-v0-c4-v1/config.json
cycy233-l3-s-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-s-v0-c4-v1/special_tokens_map.json
cycy233-l3-s-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-s-v0-c4-v1/tokenizer_config.json
cycy233-l3-s-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-s-v0-c4-v1/tokenizer.json
cycy233-l3-s-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-s-v0-c4-v1/flywheel_model.0.safetensors
cycy233-l3-s-v0-c4-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-s-v0-c4-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%|▏ | 4/291 [00:00<00:07, 38.90it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:04, 65.68it/s]
Loading 0: 8%|▊ | 22/291 [00:00<00:03, 74.03it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:03, 78.50it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:02, 89.38it/s]
Loading 0: 18%|█▊ | 51/291 [00:00<00:02, 88.93it/s]
Loading 0: 21%|██ | 61/291 [00:00<00:02, 79.51it/s]
Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 81.76it/s]
Loading 0: 27%|██▋ | 79/291 [00:00<00:02, 82.09it/s]
Loading 0: 30%|███ | 88/291 [00:02<00:09, 20.53it/s]
Loading 0: 33%|███▎ | 97/291 [00:02<00:07, 26.70it/s]
Loading 0: 36%|███▋ | 106/291 [00:02<00:05, 33.75it/s]
Loading 0: 40%|███▉ | 115/291 [00:02<00:04, 40.49it/s]
Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 48.52it/s]
Loading 0: 46%|████▌ | 134/291 [00:02<00:02, 58.07it/s]
Loading 0: 49%|████▉ | 143/291 [00:02<00:02, 64.78it/s]
Loading 0: 52%|█████▏ | 152/291 [00:02<00:01, 69.52it/s]
Loading 0: 57%|█████▋ | 166/291 [00:03<00:01, 77.88it/s]
Loading 0: 61%|██████ | 178/291 [00:03<00:01, 79.50it/s]
Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 24.22it/s]
Loading 0: 67%|██████▋ | 196/291 [00:04<00:03, 30.07it/s]
Loading 0: 70%|███████ | 205/291 [00:04<00:02, 36.49it/s]
Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 42.46it/s]
Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 48.92it/s]
Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 55.61it/s]
Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 62.29it/s]
Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 67.78it/s]
Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 72.77it/s]
Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 76.42it/s]
Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 79.42it/s]
Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 81.57it/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-s-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-s-v0-c4-v1-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-s-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-s-v0-c4-v1-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-s-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-s-v0-c4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-s-v0-c4-v1-mkmlizer: Saving duration: 1.400s
cycy233-l3-s-v0-c4-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.231s
cycy233-l3-s-v0-c4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-s-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-s-v0-c4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-s-v0-c4-v1_reward
cycy233-l3-s-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-s-v0-c4-v1_reward/special_tokens_map.json
cycy233-l3-s-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-s-v0-c4-v1_reward/config.json
cycy233-l3-s-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-s-v0-c4-v1_reward/tokenizer_config.json
cycy233-l3-s-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-s-v0-c4-v1_reward/merges.txt
cycy233-l3-s-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-s-v0-c4-v1_reward/vocab.json
cycy233-l3-s-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-s-v0-c4-v1_reward/tokenizer.json
cycy233-l3-s-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-s-v0-c4-v1_reward/reward.tensors
Job cycy233-l3-s-v0-c4-v1-mkmlizer completed after 105.2s with status: succeeded
Stopping job with name cycy233-l3-s-v0-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-s-v0-c4-v1
Waiting for inference service cycy233-l3-s-v0-c4-v1 to be ready
Inference service cycy233-l3-s-v0-c4-v1 ready after 171.06781935691833s
Pipeline stage ISVCDeployer completed in 173.49s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4288535118103027s
Received healthy response to inference request in 1.5227513313293457s
Received healthy response to inference request in 1.4789371490478516s
Received healthy response to inference request in 1.458951711654663s
Received healthy response to inference request in 1.5130424499511719s
5 requests
0 failed requests
5th percentile: 1.4629487991333008
10th percentile: 1.4669458866119385
20th percentile: 1.4749400615692139
30th percentile: 1.4857582092285155
40th percentile: 1.4994003295898437
50th percentile: 1.5130424499511719
60th percentile: 1.5169260025024414
70th percentile: 1.5208095550537108
80th percentile: 1.7039717674255372
90th percentile: 2.06641263961792
95th percentile: 2.247633075714111
99th percentile: 2.3926094245910643
mean time: 1.680507230758667
Pipeline stage StressChecker completed in 9.15s
cycy233-l3-s-v0-c4_v1 status is now deployed due to DeploymentManager action
cycy233-l3-s-v0-c4_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-s-v0-c4_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-s-v0-c4-v1 is running
Tearing down inference service cycy233-l3-s-v0-c4-v1
Service cycy233-l3-s-v0-c4-v1 has been torndown
Pipeline stage ISVCDeleter completed in 8.68s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-s-v0-c4-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-s-v0-c4-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-s-v0-c4-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-s-v0-c4-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-s-v0-c4-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-s-v0-c4-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-s-v0-c4-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-s-v0-c4-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-s-v0-c4-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-s-v0-c4-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-s-v0-c4-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-s-v0-c4-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.44s
cycy233-l3-s-v0-c4_v1 status is now torndown due to DeploymentManager action