Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ Version: 0.9.7 ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: Downloaded to shared memory in 23.882s
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpspxkv8_5, device:0
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: quantized model in 25.201s
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 49.083s
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v68
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v68/config.json
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v68/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v68/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v68/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v68/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:04<11:22, 2.36s/it]
Loading 0: 2%|▏ | 6/291 [00:04<03:01, 1.57it/s]
Loading 0: 5%|▍ | 14/291 [00:04<00:59, 4.68it/s]
Loading 0: 7%|▋ | 20/291 [00:05<00:35, 7.60it/s]
Loading 0: 9%|▉ | 27/291 [00:05<00:21, 12.02it/s]
Loading 0: 11%|█▏ | 33/291 [00:05<00:16, 15.82it/s]
Loading 0: 14%|█▍ | 42/291 [00:05<00:10, 22.88it/s]
Loading 0: 18%|█▊ | 51/291 [00:05<00:08, 29.72it/s]
Loading 0: 21%|██ | 60/291 [00:05<00:08, 28.57it/s]
Loading 0: 23%|██▎ | 68/291 [00:06<00:06, 35.22it/s]
Loading 0: 25%|██▌ | 74/291 [00:06<00:05, 38.05it/s]
Loading 0: 27%|██▋ | 80/291 [00:06<00:05, 42.03it/s]
Loading 0: 30%|██▉ | 87/291 [00:06<00:04, 42.29it/s]
Loading 0: 33%|███▎ | 96/291 [00:06<00:04, 45.72it/s]
Loading 0: 36%|███▌ | 105/291 [00:06<00:03, 48.30it/s]
Loading 0: 39%|███▉ | 114/291 [00:06<00:03, 49.48it/s]
Loading 0: 42%|████▏ | 122/291 [00:07<00:03, 55.26it/s]
Loading 0: 44%|████▍ | 128/291 [00:07<00:03, 53.83it/s]
Loading 0: 46%|████▌ | 134/291 [00:07<00:02, 54.48it/s]
Loading 0: 48%|████▊ | 141/291 [00:07<00:03, 49.70it/s]
Loading 0: 52%|█████▏ | 150/291 [00:07<00:02, 51.30it/s]
Loading 0: 54%|█████▍ | 158/291 [00:07<00:02, 57.50it/s]
Loading 0: 57%|█████▋ | 165/291 [00:07<00:02, 55.51it/s]
Loading 0: 59%|█████▉ | 171/291 [00:08<00:03, 37.96it/s]
Loading 0: 61%|██████ | 177/291 [00:08<00:02, 39.00it/s]
Loading 0: 64%|██████▍ | 186/291 [00:08<00:02, 43.87it/s]
Loading 0: 67%|██████▋ | 194/291 [00:08<00:01, 50.69it/s]
Loading 0: 69%|██████▊ | 200/291 [00:08<00:01, 50.15it/s]
Loading 0: 71%|███████ | 206/291 [00:08<00:01, 52.31it/s]
Loading 0: 73%|███████▎ | 213/291 [00:08<00:01, 50.20it/s]
Loading 0: 76%|███████▋ | 222/291 [00:09<00:01, 53.15it/s]
Loading 0: 79%|███████▉ | 231/291 [00:09<00:01, 53.38it/s]
Loading 0: 82%|████████▏ | 239/291 [00:09<00:00, 59.18it/s]
Loading 0: 85%|████████▍ | 246/291 [00:09<00:00, 58.19it/s]
Loading 0: 87%|████████▋ | 253/291 [00:09<00:00, 59.61it/s]
Loading 0: 89%|████████▉ | 260/291 [00:09<00:00, 56.17it/s]
Loading 0: 91%|█████████▏| 266/291 [00:10<00:00, 41.32it/s]
Loading 0: 93%|█████████▎| 272/291 [00:10<00:00, 41.67it/s]
Loading 0: 95%|█████████▌| 277/291 [00:10<00:00, 43.30it/s]
Loading 0: 98%|█████████▊| 285/291 [00:10<00:00, 45.84it/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.
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v68-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.
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v68-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.
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer:
Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]
Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.13s/it]
Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.72s/it]
Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.94s/it]
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.42it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 4.02it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.66it/s]
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: Saving duration: 1.377s
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 12.909s
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v68_reward
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v68_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v68_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v68_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v68_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v68_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v68_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v68_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer completed after 96.07s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v68-mkmlizer
Pipeline stage MKMLizer completed in 97.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v68
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v68 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v68 ready after 130.94861555099487s
Pipeline stage ISVCDeployer completed in 132.46s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8406884670257568s
Received healthy response to inference request in 1.0586357116699219s
Received healthy response to inference request in 1.1194384098052979s
Received healthy response to inference request in 0.7870199680328369s
Received healthy response to inference request in 1.1154639720916748s
5 requests
0 failed requests
5th percentile: 0.8413431167602539
10th percentile: 0.8956662654876709
20th percentile: 1.004312562942505
30th percentile: 1.0700013637542725
40th percentile: 1.0927326679229736
50th percentile: 1.1154639720916748
60th percentile: 1.117053747177124
70th percentile: 1.1186435222625732
80th percentile: 1.2636884212493897
90th percentile: 1.5521884441375733
95th percentile: 1.696438455581665
99th percentile: 1.8118384647369385
mean time: 1.1842493057250976
Pipeline stage StressChecker completed in 6.62s
chaiml-sao10k-l3-rp-v3-3_v68 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v68 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v68
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v68 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v68
Service chaiml-sao10k-l3-rp-v3-3-v68 has been torndown
Pipeline stage ISVCDeleter completed in 5.30s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v68/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v68/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v68/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v68/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v68/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v68_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v68_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v68_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v68_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v68_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v68_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v68_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.37s
chaiml-sao10k-l3-rp-v3-3_v68 status is now torndown due to DeploymentManager action