Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ Version: 0.9.7 ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: Downloaded to shared memory in 23.360s
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp19296t1k, device:0
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: quantized model in 26.062s
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 49.423s
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v66
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v66/config.json
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v66/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v66/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v66/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:04<11:27, 2.38s/it]
Loading 0: 2%|▏ | 6/291 [00:04<03:03, 1.56it/s]
Loading 0: 5%|▍ | 14/291 [00:05<00:59, 4.63it/s]
Loading 0: 7%|▋ | 20/291 [00:05<00:36, 7.47it/s]
Loading 0: 9%|▊ | 25/291 [00:05<00:25, 10.38it/s]
Loading 0: 11%|█▏ | 33/291 [00:05<00:16, 15.66it/s]
Loading 0: 14%|█▍ | 41/291 [00:05<00:11, 22.46it/s]
Loading 0: 16%|█▌ | 47/291 [00:05<00:09, 25.92it/s]
Loading 0: 18%|█▊ | 53/291 [00:05<00:07, 30.59it/s]
Loading 0: 21%|██ | 60/291 [00:06<00:08, 26.44it/s]
Loading 0: 23%|██▎ | 68/291 [00:06<00:06, 34.44it/s]
Loading 0: 25%|██▌ | 74/291 [00:06<00:05, 36.36it/s]
Loading 0: 27%|██▋ | 80/291 [00:06<00:05, 39.48it/s]
Loading 0: 30%|██▉ | 86/291 [00:06<00:04, 43.51it/s]
Loading 0: 32%|███▏ | 92/291 [00:06<00:04, 43.04it/s]
Loading 0: 33%|███▎ | 97/291 [00:06<00:04, 42.98it/s]
Loading 0: 35%|███▌ | 103/291 [00:06<00:04, 46.74it/s]
Loading 0: 37%|███▋ | 109/291 [00:07<00:03, 47.48it/s]
Loading 0: 40%|███▉ | 115/291 [00:07<00:04, 41.15it/s]
Loading 0: 42%|████▏ | 121/291 [00:07<00:03, 44.34it/s]
Loading 0: 43%|████▎ | 126/291 [00:07<00:03, 44.45it/s]
Loading 0: 45%|████▌ | 131/291 [00:07<00:03, 45.82it/s]
Loading 0: 47%|████▋ | 137/291 [00:07<00:03, 44.48it/s]
Loading 0: 49%|████▉ | 142/291 [00:07<00:03, 44.22it/s]
Loading 0: 51%|█████ | 149/291 [00:07<00:02, 50.09it/s]
Loading 0: 53%|█████▎ | 155/291 [00:08<00:02, 47.80it/s]
Loading 0: 55%|█████▍ | 160/291 [00:08<00:02, 47.37it/s]
Loading 0: 57%|█████▋ | 166/291 [00:08<00:03, 36.57it/s]
Loading 0: 59%|█████▉ | 171/291 [00:08<00:03, 38.61it/s]
Loading 0: 60%|██████ | 176/291 [00:08<00:02, 40.66it/s]
Loading 0: 62%|██████▏ | 181/291 [00:08<00:02, 42.72it/s]
Loading 0: 64%|██████▍ | 186/291 [00:08<00:02, 39.02it/s]
Loading 0: 67%|██████▋ | 194/291 [00:09<00:01, 48.50it/s]
Loading 0: 69%|██████▊ | 200/291 [00:09<00:01, 47.08it/s]
Loading 0: 70%|███████ | 205/291 [00:09<00:01, 46.91it/s]
Loading 0: 73%|███████▎ | 213/291 [00:09<00:01, 46.90it/s]
Loading 0: 76%|███████▌ | 221/291 [00:09<00:01, 53.66it/s]
Loading 0: 78%|███████▊ | 227/291 [00:09<00:01, 50.96it/s]
Loading 0: 80%|████████ | 233/291 [00:09<00:01, 50.03it/s]
Loading 0: 82%|████████▏ | 240/291 [00:09<00:01, 46.80it/s]
Loading 0: 85%|████████▌ | 248/291 [00:10<00:00, 53.81it/s]
Loading 0: 87%|████████▋ | 254/291 [00:10<00:00, 50.11it/s]
Loading 0: 89%|████████▉ | 260/291 [00:10<00:00, 50.85it/s]
Loading 0: 91%|█████████▏| 266/291 [00:10<00:00, 37.70it/s]
Loading 0: 93%|█████████▎| 272/291 [00:10<00:00, 38.56it/s]
Loading 0: 95%|█████████▌| 277/291 [00:10<00:00, 40.19it/s]
Loading 0: 98%|█████████▊| 284/291 [00:10<00:00, 46.71it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 44.96it/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-v66-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v66-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-v66-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v66-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-v66-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer:
Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]
Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.47s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.29s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.62s/it]
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.46it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 4.04it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.68it/s]
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: Saving duration: 1.346s
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.313s
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v66_reward
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v66_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v66_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v66_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v66_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v66_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v66_reward/tokenizer.json
Job chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer completed after 96.27s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v66-mkmlizer
Pipeline stage MKMLizer completed in 97.34s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v66
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v66 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v66 ready after 121.32772755622864s
Pipeline stage ISVCDeployer completed in 123.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.175589084625244s
Received healthy response to inference request in 1.2174224853515625s
Received healthy response to inference request in 1.2651009559631348s
Received healthy response to inference request in 1.2505090236663818s
Received healthy response to inference request in 1.2363693714141846s
5 requests
0 failed requests
5th percentile: 1.2212118625640869
10th percentile: 1.2250012397766112
20th percentile: 1.2325799942016602
30th percentile: 1.239197301864624
40th percentile: 1.2448531627655028
50th percentile: 1.2505090236663818
60th percentile: 1.256345796585083
70th percentile: 1.2621825695037843
80th percentile: 1.4471985816955568
90th percentile: 1.8113938331604005
95th percentile: 1.993491458892822
99th percentile: 2.1391695594787596
mean time: 1.4289981842041015
Pipeline stage StressChecker completed in 7.82s
chaiml-sao10k-l3-rp-v3-3_v66 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v66 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v66
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v66 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v66
Service chaiml-sao10k-l3-rp-v3-3-v66 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 chaiml-sao10k-l3-rp-v3-3-v66/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v66/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v66/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v66/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v66/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v66_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v66_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v66_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v66_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v66_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v66_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v66_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.58s
chaiml-sao10k-l3-rp-v3-3_v66 status is now torndown due to DeploymentManager action