Running pipeline stage MKMLizer
Starting job with name cycy233-l3-ss-e-v3-c2-v1-mkmlizer
Waiting for job on cycy233-l3-ss-e-v3-c2-v1-mkmlizer to finish
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ /___/ ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ Version: 0.9.9 ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ║ ║
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: Downloaded to shared memory in 30.834s
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjsy8av10, device:0
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: quantized model in 26.773s
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: Processed model cycy233/L3-ss-e-v3-c2 in 57.607s
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ss-e-v3-c2-v1
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ss-e-v3-c2-v1/config.json
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ss-e-v3-c2-v1/special_tokens_map.json
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ss-e-v3-c2-v1/tokenizer_config.json
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ss-e-v3-c2-v1/tokenizer.json
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ss-e-v3-c2-v1/flywheel_model.0.safetensors
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-ss-e-v3-c2-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:08, 31.80it/s]
Loading 0: 4%|▍ | 12/291 [00:00<00:05, 49.68it/s]
Loading 0: 6%|▌ | 18/291 [00:00<00:05, 50.85it/s]
Loading 0: 8%|▊ | 24/291 [00:00<00:06, 41.78it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:05, 47.55it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 43.48it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 42.78it/s]
Loading 0: 17%|█▋ | 49/291 [00:01<00:05, 48.20it/s]
Loading 0: 19%|█▉ | 55/291 [00:01<00:05, 44.50it/s]
Loading 0: 21%|██ | 60/291 [00:01<00:05, 43.32it/s]
Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 47.89it/s]
Loading 0: 25%|██▍ | 72/291 [00:01<00:04, 47.83it/s]
Loading 0: 26%|██▋ | 77/291 [00:01<00:05, 39.60it/s]
Loading 0: 29%|██▊ | 83/291 [00:02<00:06, 31.87it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 31.36it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 38.03it/s]
Loading 0: 34%|███▍ | 99/291 [00:02<00:04, 40.46it/s]
Loading 0: 36%|███▌ | 104/291 [00:02<00:05, 35.02it/s]
Loading 0: 38%|███▊ | 111/291 [00:02<00:04, 41.28it/s]
Loading 0: 40%|███▉ | 116/291 [00:02<00:04, 42.40it/s]
Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 43.16it/s]
Loading 0: 44%|████▎ | 127/291 [00:03<00:03, 42.08it/s]
Loading 0: 45%|████▌ | 132/291 [00:03<00:03, 41.77it/s]
Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 47.46it/s]
Loading 0: 49%|████▉ | 144/291 [00:03<00:03, 47.24it/s]
Loading 0: 51%|█████ | 149/291 [00:03<00:03, 38.59it/s]
Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 46.53it/s]
Loading 0: 56%|█████▌ | 162/291 [00:03<00:02, 47.13it/s]
Loading 0: 57%|█████▋ | 167/291 [00:04<00:03, 38.33it/s]
Loading 0: 59%|█████▉ | 173/291 [00:04<00:02, 42.56it/s]
Loading 0: 62%|██████▏ | 179/291 [00:04<00:02, 45.99it/s]
Loading 0: 63%|██████▎ | 184/291 [00:04<00:02, 44.98it/s]
Loading 0: 65%|██████▍ | 189/291 [00:04<00:03, 27.27it/s]
Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 29.72it/s]
Loading 0: 69%|██████▉ | 201/291 [00:04<00:02, 37.43it/s]
Loading 0: 71%|███████ | 206/291 [00:05<00:02, 38.92it/s]
Loading 0: 73%|███████▎ | 211/291 [00:05<00:01, 40.96it/s]
Loading 0: 74%|███████▍ | 216/291 [00:05<00:01, 42.54it/s]
Loading 0: 76%|███████▌ | 221/291 [00:05<00:01, 36.05it/s]
Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 44.67it/s]
Loading 0: 81%|████████ | 235/291 [00:05<00:01, 43.87it/s]
Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 43.65it/s]
Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 48.93it/s]
Loading 0: 87%|████████▋ | 253/291 [00:06<00:00, 47.72it/s]
Loading 0: 89%|████████▊ | 258/291 [00:06<00:00, 45.68it/s]
Loading 0: 91%|█████████ | 264/291 [00:06<00:00, 49.18it/s]
Loading 0: 93%|█████████▎| 270/291 [00:06<00:00, 48.65it/s]
Loading 0: 95%|█████████▍| 275/291 [00:06<00:00, 41.73it/s]
Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 42.43it/s]
Loading 0: 99%|█████████▊| 287/291 [00:12<00:01, 3.35it/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-ss-e-v3-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ss-e-v3-c2-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-ss-e-v3-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ss-e-v3-c2-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-ss-e-v3-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: Saving duration: 1.443s
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.964s
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c2-v1_reward
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c2-v1_reward/config.json
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c2-v1_reward/special_tokens_map.json
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c2-v1_reward/tokenizer_config.json
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c2-v1_reward/merges.txt
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c2-v1_reward/vocab.json
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c2-v1_reward/tokenizer.json
cycy233-l3-ss-e-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c2-v1_reward/reward.tensors
Job cycy233-l3-ss-e-v3-c2-v1-mkmlizer completed after 101.67s with status: succeeded
Stopping job with name cycy233-l3-ss-e-v3-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 103.14s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ss-e-v3-c2-v1
Waiting for inference service cycy233-l3-ss-e-v3-c2-v1 to be ready
Inference service cycy233-l3-ss-e-v3-c2-v1 ready after 301.61867117881775s
Pipeline stage ISVCDeployer completed in 303.44s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.550719738006592s
Received healthy response to inference request in 1.582430362701416s
Received healthy response to inference request in 1.4997332096099854s
Received healthy response to inference request in 1.4752724170684814s
Received healthy response to inference request in 1.5552189350128174s
5 requests
0 failed requests
5th percentile: 1.4801645755767823
10th percentile: 1.485056734085083
20th percentile: 1.4948410511016845
30th percentile: 1.5108303546905517
40th percentile: 1.5330246448516847
50th percentile: 1.5552189350128174
60th percentile: 1.5661035060882569
70th percentile: 1.5769880771636964
80th percentile: 1.7760882377624514
90th percentile: 2.1634039878845215
95th percentile: 2.3570618629455566
99th percentile: 2.5119881629943848
mean time: 1.7326749324798585
Pipeline stage StressChecker completed in 9.43s
cycy233-l3-ss-e-v3-c2_v1 status is now deployed due to DeploymentManager action
cycy233-l3-ss-e-v3-c2_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-ss-e-v3-c2_v1 status is now torndown due to DeploymentManager action