Running pipeline stage MKMLizer
Starting job with name cycy233-l3-e-v2-c1-v13-mkmlizer
Waiting for job on cycy233-l3-e-v2-c1-v13-mkmlizer to finish
cycy233-l3-e-v2-c1-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ _____ __ __ ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ /___/ ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ Version: 0.9.5.post3 ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ belonging to: ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c1-v13-mkmlizer: Downloaded to shared memory in 22.096s
cycy233-l3-e-v2-c1-v13-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfydxz3qs, device:0
cycy233-l3-e-v2-c1-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c1-v13-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:02, 121.62it/s]
Loading 0: 10%|█ | 30/291 [00:00<00:01, 139.27it/s]
Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 135.48it/s]
Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 133.24it/s]
Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 138.32it/s]
Loading 0: 31%|███ | 89/291 [00:00<00:02, 83.80it/s]
Loading 0: 35%|███▌ | 103/291 [00:00<00:02, 93.50it/s]
Loading 0: 41%|████ | 120/291 [00:01<00:01, 106.94it/s]
Loading 0: 46%|████▌ | 133/291 [00:01<00:01, 109.17it/s]
Loading 0: 51%|█████ | 148/291 [00:01<00:01, 114.36it/s]
Loading 0: 56%|█████▌ | 162/291 [00:01<00:01, 120.59it/s]
Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 127.90it/s]
Loading 0: 66%|██████▋ | 193/291 [00:01<00:01, 85.46it/s]
Loading 0: 72%|███████▏ | 210/291 [00:01<00:00, 99.46it/s]
Loading 0: 77%|███████▋ | 223/291 [00:02<00:00, 105.75it/s]
Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 113.28it/s]
Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 122.35it/s]
Loading 0: 92%|█████████▏| 269/291 [00:02<00:00, 123.67it/s]
Loading 0: 97%|█████████▋| 283/291 [00:02<00:00, 125.27it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-e-v2-c1-v13-mkmlizer: quantized model in 22.222s
cycy233-l3-e-v2-c1-v13-mkmlizer: Processed model cycy233/L3-e-v2-c1 in 44.319s
cycy233-l3-e-v2-c1-v13-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c1-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c1-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v13
cycy233-l3-e-v2-c1-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v13/config.json
cycy233-l3-e-v2-c1-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v13/special_tokens_map.json
cycy233-l3-e-v2-c1-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v13/tokenizer_config.json
cycy233-l3-e-v2-c1-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v13/flywheel_model.0.safetensors
cycy233-l3-e-v2-c1-v13-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v2-c1-v13-mkmlizer: /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.
cycy233-l3-e-v2-c1-v13-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c1-v13-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.
cycy233-l3-e-v2-c1-v13-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c1-v13-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-e-v2-c1-v13-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c1-v13-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c1-v13-mkmlizer: Saving duration: 1.365s
cycy233-l3-e-v2-c1-v13-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.951s
cycy233-l3-e-v2-c1-v13-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c1-v13-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c1-v13-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v13_reward
cycy233-l3-e-v2-c1-v13-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v13_reward/config.json
cycy233-l3-e-v2-c1-v13-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v13_reward/special_tokens_map.json
cycy233-l3-e-v2-c1-v13-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v13_reward/tokenizer_config.json
cycy233-l3-e-v2-c1-v13-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v13_reward/reward.tensors
Job cycy233-l3-e-v2-c1-v13-mkmlizer completed after 84.72s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c1-v13-mkmlizer
Pipeline stage MKMLizer completed in 85.73s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.07s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c1-v13
Waiting for inference service cycy233-l3-e-v2-c1-v13 to be ready
Inference service cycy233-l3-e-v2-c1-v13 ready after 61.27559733390808s
Pipeline stage ISVCDeployer completed in 63.32s
Running pipeline stage StressChecker
Failed to get response for submission undi95-meta-llama-3-70b_6209_v18: ('http://undi95-meta-llama-3-70b-6209-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Received healthy response to inference request in 2.0739426612854004s
Received healthy response to inference request in 1.2637498378753662s
Received healthy response to inference request in 1.2684521675109863s
Received healthy response to inference request in 1.3227012157440186s
Failed to get response for submission undi95-meta-llama-3-70b_6209_v18: ('http://undi95-meta-llama-3-70b-6209-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Received healthy response to inference request in 1.4489355087280273s
5 requests
0 failed requests
5th percentile: 1.2646903038024901
10th percentile: 1.2656307697296143
20th percentile: 1.2675117015838624
30th percentile: 1.2793019771575929
40th percentile: 1.3010015964508057
50th percentile: 1.3227012157440186
60th percentile: 1.373194932937622
70th percentile: 1.4236886501312256
80th percentile: 1.573936939239502
90th percentile: 1.8239398002624512
95th percentile: 1.9489412307739258
99th percentile: 2.0489423751831053
mean time: 1.4755562782287597
Pipeline stage StressChecker completed in 8.01s
cycy233-l3-e-v2-c1_v13 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c1_v13 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c1_v13
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c1-v13 is running
Tearing down inference service cycy233-l3-e-v2-c1-v13
Service cycy233-l3-e-v2-c1-v13 has been torndown
Pipeline stage ISVCDeleter completed in 5.01s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v13/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v13/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v13/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v13/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v13/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v13_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v13_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v13_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v13_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v13_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v13_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v13_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.41s
cycy233-l3-e-v2-c1_v13 status is now torndown due to DeploymentManager action