Running pipeline stage MKMLizer
Starting job with name cycy233-l3-ss-e-v3-c4-v1-mkmlizer
Waiting for job on cycy233-l3-ss-e-v3-c4-v1-mkmlizer to finish
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ /___/ ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ Version: 0.9.9 ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ║ ║
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: Downloaded to shared memory in 27.669s
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5vp3n25v, device:0
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: quantized model in 26.376s
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: Processed model cycy233/L3-ss-e-v3-c4 in 54.046s
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ss-e-v3-c4-v1
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ss-e-v3-c4-v1/config.json
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ss-e-v3-c4-v1/special_tokens_map.json
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ss-e-v3-c4-v1/tokenizer_config.json
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ss-e-v3-c4-v1/tokenizer.json
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ss-e-v3-c4-v1/flywheel_model.0.safetensors
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-ss-e-v3-c4-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:08, 35.46it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:04, 57.00it/s]
Loading 0: 7%|▋ | 20/291 [00:00<00:05, 52.57it/s]
Loading 0: 9%|▉ | 26/291 [00:00<00:05, 51.18it/s]
Loading 0: 11%|█ | 32/291 [00:00<00:06, 42.02it/s]
Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 51.13it/s]
Loading 0: 16%|█▌ | 46/291 [00:00<00:05, 47.81it/s]
Loading 0: 18%|█▊ | 52/291 [00:01<00:04, 49.36it/s]
Loading 0: 20%|█▉ | 58/291 [00:01<00:04, 51.94it/s]
Loading 0: 22%|██▏ | 64/291 [00:01<00:04, 46.12it/s]
Loading 0: 24%|██▎ | 69/291 [00:01<00:04, 45.25it/s]
Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 50.39it/s]
Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 46.22it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 31.85it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 38.42it/s]
Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 38.56it/s]
Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 39.03it/s]
Loading 0: 38%|███▊ | 111/291 [00:02<00:04, 43.50it/s]
Loading 0: 40%|███▉ | 116/291 [00:02<00:04, 42.52it/s]
Loading 0: 42%|████▏ | 121/291 [00:02<00:04, 42.49it/s]
Loading 0: 43%|████▎ | 126/291 [00:02<00:03, 44.02it/s]
Loading 0: 45%|████▌ | 131/291 [00:03<00:04, 36.19it/s]
Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 44.67it/s]
Loading 0: 49%|████▉ | 144/291 [00:03<00:03, 45.66it/s]
Loading 0: 51%|█████ | 149/291 [00:03<00:03, 39.92it/s]
Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 48.19it/s]
Loading 0: 56%|█████▌ | 163/291 [00:03<00:02, 45.52it/s]
Loading 0: 58%|█████▊ | 168/291 [00:03<00:02, 44.95it/s]
Loading 0: 60%|██████ | 176/291 [00:03<00:02, 53.19it/s]
Loading 0: 63%|██████▎ | 182/291 [00:04<00:02, 45.15it/s]
Loading 0: 64%|██████▍ | 187/291 [00:04<00:02, 35.48it/s]
Loading 0: 66%|██████▌ | 192/291 [00:04<00:02, 36.95it/s]
Loading 0: 68%|██████▊ | 197/291 [00:04<00:02, 39.09it/s]
Loading 0: 70%|██████▉ | 203/291 [00:04<00:02, 37.51it/s]
Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 46.13it/s]
Loading 0: 75%|███████▍ | 217/291 [00:04<00:01, 44.32it/s]
Loading 0: 76%|███████▋ | 222/291 [00:05<00:01, 44.04it/s]
Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 49.10it/s]
Loading 0: 81%|████████ | 235/291 [00:05<00:01, 45.00it/s]
Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 44.40it/s]
Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 49.49it/s]
Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 46.39it/s]
Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 45.21it/s]
Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 50.33it/s]
Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 44.85it/s]
Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 43.07it/s]
Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 39.94it/s]
Loading 0: 99%|█████████▊| 287/291 [00:11<00:01, 3.25it/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-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-ss-e-v3-c4-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-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-ss-e-v3-c4-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-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: Saving duration: 1.403s
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 12.094s
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c4-v1_reward
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c4-v1_reward/tokenizer_config.json
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c4-v1_reward/special_tokens_map.json
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c4-v1_reward/config.json
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c4-v1_reward/merges.txt
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c4-v1_reward/vocab.json
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c4-v1_reward/tokenizer.json
cycy233-l3-ss-e-v3-c4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ss-e-v3-c4-v1_reward/reward.tensors
Job cycy233-l3-ss-e-v3-c4-v1-mkmlizer completed after 104.39s with status: succeeded
Stopping job with name cycy233-l3-ss-e-v3-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.26s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ss-e-v3-c4-v1
Waiting for inference service cycy233-l3-ss-e-v3-c4-v1 to be ready
Failed to get response for submission cycy233-l3-ss-e-v2-c1_v3: ('http://cycy233-l3-ss-e-v2-c1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:40936->127.0.0.1:8080: read: connection reset by peer\n')
Inference service cycy233-l3-ss-e-v3-c4-v1 ready after 290.8569493293762s
Pipeline stage ISVCDeployer completed in 293.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.32128643989563s
Received healthy response to inference request in 1.4965252876281738s
Received healthy response to inference request in 1.47408127784729s
Received healthy response to inference request in 1.444152593612671s
Received healthy response to inference request in 1.5101191997528076s
5 requests
0 failed requests
5th percentile: 1.4501383304595947
10th percentile: 1.4561240673065186
20th percentile: 1.4680955410003662
30th percentile: 1.4785700798034669
40th percentile: 1.4875476837158204
50th percentile: 1.4965252876281738
60th percentile: 1.5019628524780273
70th percentile: 1.5074004173278808
80th percentile: 1.6723526477813722
90th percentile: 1.996819543838501
95th percentile: 2.1590529918670653
99th percentile: 2.288839750289917
mean time: 1.6492329597473145
Pipeline stage StressChecker completed in 9.03s
cycy233-l3-ss-e-v3-c4_v1 status is now deployed due to DeploymentManager action
cycy233-l3-ss-e-v3-c4_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-ss-e-v3-c4_v1 status is now torndown due to DeploymentManager action