Running pipeline stage MKMLizer
Starting job with name sao10k-l3-tamamo-3-1-v1-mkmlizer
Waiting for job on sao10k-l3-tamamo-3-1-v1-mkmlizer to finish
sao10k-l3-tamamo-3-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ _____ __ __ ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ /___/ ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ Version: 0.9.9 ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ belonging to: ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ║ ║
sao10k-l3-tamamo-3-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-tamamo-3-1-v1-mkmlizer: Downloaded to shared memory in 26.991s
sao10k-l3-tamamo-3-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppoug7uax, device:0
sao10k-l3-tamamo-3-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-tamamo-3-1-v1-mkmlizer: quantized model in 25.987s
sao10k-l3-tamamo-3-1-v1-mkmlizer: Processed model Sao10K/L3-Tamamo-3.1 in 52.978s
sao10k-l3-tamamo-3-1-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-tamamo-3-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-tamamo-3-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-tamamo-3-1-v1
sao10k-l3-tamamo-3-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-tamamo-3-1-v1/config.json
sao10k-l3-tamamo-3-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-tamamo-3-1-v1/special_tokens_map.json
sao10k-l3-tamamo-3-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-tamamo-3-1-v1/tokenizer_config.json
sao10k-l3-tamamo-3-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-tamamo-3-1-v1/tokenizer.json
sao10k-l3-tamamo-3-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-tamamo-3-1-v1/flywheel_model.0.safetensors
sao10k-l3-tamamo-3-1-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
sao10k-l3-tamamo-3-1-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:04<11:34, 2.40s/it]
Loading 0: 2%|▏ | 6/291 [00:04<03:04, 1.54it/s]
Loading 0: 4%|▍ | 13/291 [00:05<01:05, 4.22it/s]
Loading 0: 7%|▋ | 20/291 [00:05<00:36, 7.50it/s]
Loading 0: 9%|▊ | 25/291 [00:05<00:25, 10.40it/s]
Loading 0: 11%|█▏ | 33/291 [00:05<00:16, 15.68it/s]
Loading 0: 14%|█▍ | 41/291 [00:05<00:11, 22.55it/s]
Loading 0: 16%|█▌ | 47/291 [00:05<00:09, 25.90it/s]
Loading 0: 18%|█▊ | 53/291 [00:05<00:07, 29.93it/s]
Loading 0: 20%|██ | 59/291 [00:05<00:06, 34.89it/s]
Loading 0: 22%|██▏ | 65/291 [00:06<00:06, 36.39it/s]
Loading 0: 24%|██▍ | 70/291 [00:06<00:05, 38.25it/s]
Loading 0: 26%|██▋ | 77/291 [00:06<00:04, 44.57it/s]
Loading 0: 29%|██▊ | 83/291 [00:06<00:06, 30.64it/s]
Loading 0: 30%|███ | 88/291 [00:06<00:06, 33.06it/s]
Loading 0: 32%|███▏ | 94/291 [00:06<00:05, 38.18it/s]
Loading 0: 34%|███▍ | 99/291 [00:06<00:04, 39.00it/s]
Loading 0: 36%|███▌ | 104/291 [00:07<00:04, 41.15it/s]
Loading 0: 38%|███▊ | 110/291 [00:07<00:04, 40.63it/s]
Loading 0: 40%|███▉ | 115/291 [00:07<00:04, 42.14it/s]
Loading 0: 42%|████▏ | 122/291 [00:07<00:03, 47.52it/s]
Loading 0: 44%|████▍ | 128/291 [00:07<00:03, 45.62it/s]
Loading 0: 46%|████▌ | 133/291 [00:07<00:03, 46.12it/s]
Loading 0: 48%|████▊ | 140/291 [00:07<00:02, 51.81it/s]
Loading 0: 50%|█████ | 146/291 [00:07<00:02, 48.44it/s]
Loading 0: 52%|█████▏ | 152/291 [00:08<00:02, 49.82it/s]
Loading 0: 54%|█████▍ | 158/291 [00:08<00:02, 51.90it/s]
Loading 0: 56%|█████▋ | 164/291 [00:08<00:02, 48.56it/s]
Loading 0: 58%|█████▊ | 169/291 [00:08<00:02, 47.54it/s]
Loading 0: 60%|██████ | 176/291 [00:08<00:02, 52.96it/s]
Loading 0: 63%|██████▎ | 182/291 [00:08<00:02, 49.46it/s]
Loading 0: 65%|██████▍ | 188/291 [00:08<00:02, 49.99it/s]
Loading 0: 67%|██████▋ | 195/291 [00:08<00:02, 46.86it/s]
Loading 0: 70%|██████▉ | 203/291 [00:09<00:01, 54.60it/s]
Loading 0: 72%|███████▏ | 209/291 [00:09<00:02, 35.26it/s]
Loading 0: 74%|███████▎ | 214/291 [00:09<00:02, 37.31it/s]
Loading 0: 76%|███████▌ | 221/291 [00:09<00:01, 42.95it/s]
Loading 0: 78%|███████▊ | 227/291 [00:09<00:01, 42.65it/s]
Loading 0: 80%|███████▉ | 232/291 [00:09<00:01, 43.84it/s]
Loading 0: 82%|████████▏ | 239/291 [00:09<00:01, 50.10it/s]
Loading 0: 84%|████████▍ | 245/291 [00:10<00:00, 47.46it/s]
Loading 0: 86%|████████▋ | 251/291 [00:10<00:00, 49.00it/s]
Loading 0: 88%|████████▊ | 257/291 [00:10<00:00, 51.75it/s]
Loading 0: 90%|█████████ | 263/291 [00:10<00:00, 48.88it/s]
Loading 0: 92%|█████████▏| 269/291 [00:10<00:00, 50.05it/s]
Loading 0: 95%|█████████▍| 276/291 [00:10<00:00, 46.50it/s]
Loading 0: 98%|█████████▊| 284/291 [00:10<00:00, 52.99it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 47.17it/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.
sao10k-l3-tamamo-3-1-v1-mkmlizer: warnings.warn(
sao10k-l3-tamamo-3-1-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.
sao10k-l3-tamamo-3-1-v1-mkmlizer: warnings.warn(
sao10k-l3-tamamo-3-1-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.
sao10k-l3-tamamo-3-1-v1-mkmlizer: warnings.warn(
sao10k-l3-tamamo-3-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-tamamo-3-1-v1-mkmlizer: Saving duration: 1.428s
sao10k-l3-tamamo-3-1-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.339s
sao10k-l3-tamamo-3-1-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-tamamo-3-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-tamamo-3-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-tamamo-3-1-v1_reward
sao10k-l3-tamamo-3-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-tamamo-3-1-v1_reward/config.json
sao10k-l3-tamamo-3-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-tamamo-3-1-v1_reward/tokenizer_config.json
sao10k-l3-tamamo-3-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-tamamo-3-1-v1_reward/special_tokens_map.json
sao10k-l3-tamamo-3-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-tamamo-3-1-v1_reward/merges.txt
sao10k-l3-tamamo-3-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-tamamo-3-1-v1_reward/vocab.json
sao10k-l3-tamamo-3-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-tamamo-3-1-v1_reward/tokenizer.json
sao10k-l3-tamamo-3-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-tamamo-3-1-v1_reward/reward.tensors
Job sao10k-l3-tamamo-3-1-v1-mkmlizer completed after 94.55s with status: succeeded
Stopping job with name sao10k-l3-tamamo-3-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-tamamo-3-1-v1
Waiting for inference service sao10k-l3-tamamo-3-1-v1 to be ready
Inference service sao10k-l3-tamamo-3-1-v1 ready after 151.12564659118652s
Pipeline stage ISVCDeployer completed in 153.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3722283840179443s
Received healthy response to inference request in 1.4817464351654053s
Received healthy response to inference request in 1.4461777210235596s
Received healthy response to inference request in 1.431856393814087s
Received healthy response to inference request in 1.4872655868530273s
5 requests
0 failed requests
5th percentile: 1.4347206592559814
10th percentile: 1.437584924697876
20th percentile: 1.4433134555816651
30th percentile: 1.4532914638519288
40th percentile: 1.467518949508667
50th percentile: 1.4817464351654053
60th percentile: 1.483954095840454
70th percentile: 1.486161756515503
80th percentile: 1.6642581462860109
90th percentile: 2.0182432651519777
95th percentile: 2.1952358245849606
99th percentile: 2.3368298721313474
mean time: 1.6438549041748047
Pipeline stage StressChecker completed in 8.85s
sao10k-l3-tamamo-3-1_v1 status is now deployed due to DeploymentManager action
sao10k-l3-tamamo-3-1_v1 status is now inactive due to auto deactivation removed underperforming models
sao10k-l3-tamamo-3-1_v1 status is now torndown due to DeploymentManager action
Deleting key trace2333-fd-llama3-v1-f-7971-v1_reward/vocab.json from bucket guanaco-reward-models