Running pipeline stage MKMLizer
Starting job with name cgato-l3-1-thegreenlion-6585-v1-mkmlizer
Waiting for job on cgato-l3-1-thegreenlion-6585-v1-mkmlizer to finish
Stopping job with name cgato-l3-1-thegreenlion-6585-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name cgato-l3-1-thegreenlion-6585-v1-mkmlizer
Waiting for job on cgato-l3-1-thegreenlion-6585-v1-mkmlizer to finish
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ /___/ ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ Version: 0.9.9 ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ https://mk1.ai ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ belonging to: ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ║ ║
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: Downloaded to shared memory in 32.787s
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpekvdt2aa, device:0
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: quantized model in 26.618s
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: Processed model cgato/L3.1-TheGreenLion-8b-SFT-v0.2.2 in 59.406s
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-1-thegreenlion-6585-v1
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-1-thegreenlion-6585-v1/config.json
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-1-thegreenlion-6585-v1/special_tokens_map.json
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-1-thegreenlion-6585-v1/tokenizer_config.json
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-1-thegreenlion-6585-v1/tokenizer.json
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-1-thegreenlion-6585-v1/flywheel_model.0.safetensors
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
cgato-l3-1-thegreenlion-6585-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:08, 35.07it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:05, 53.90it/s]
Loading 0: 7%|▋ | 19/291 [00:00<00:05, 46.78it/s]
Loading 0: 8%|▊ | 24/291 [00:00<00:05, 45.67it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:05, 50.68it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 44.66it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 44.54it/s]
Loading 0: 17%|█▋ | 49/291 [00:01<00:04, 50.32it/s]
Loading 0: 19%|█▉ | 55/291 [00:01<00:05, 45.96it/s]
Loading 0: 21%|██ | 60/291 [00:01<00:05, 44.95it/s]
Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 49.31it/s]
Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 43.99it/s]
Loading 0: 27%|██▋ | 78/291 [00:01<00:04, 43.92it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:06, 31.79it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 32.17it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 38.94it/s]
Loading 0: 34%|███▍ | 99/291 [00:02<00:04, 41.04it/s]
Loading 0: 36%|███▌ | 104/291 [00:02<00:05, 34.69it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 43.11it/s]
Loading 0: 40%|████ | 117/291 [00:02<00:03, 44.60it/s]
Loading 0: 42%|████▏ | 122/291 [00:02<00:04, 37.26it/s]
Loading 0: 44%|████▍ | 129/291 [00:03<00:03, 43.69it/s]
Loading 0: 46%|████▌ | 134/291 [00:03<00:03, 42.47it/s]
Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 42.93it/s]
Loading 0: 49%|████▉ | 144/291 [00:03<00:03, 44.29it/s]
Loading 0: 51%|█████ | 149/291 [00:03<00:03, 37.16it/s]
Loading 0: 54%|█████▎ | 156/291 [00:03<00:03, 43.98it/s]
Loading 0: 55%|█████▌ | 161/291 [00:03<00:02, 43.52it/s]
Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 44.16it/s]
Loading 0: 59%|█████▉ | 172/291 [00:04<00:02, 41.49it/s]
Loading 0: 62%|██████▏ | 179/291 [00:04<00:02, 45.55it/s]
Loading 0: 63%|██████▎ | 184/291 [00:04<00:02, 44.21it/s]
Loading 0: 65%|██████▍ | 189/291 [00:04<00:03, 27.81it/s]
Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 30.11it/s]
Loading 0: 69%|██████▉ | 201/291 [00:04<00:02, 37.76it/s]
Loading 0: 71%|███████ | 206/291 [00:05<00:02, 39.60it/s]
Loading 0: 73%|███████▎ | 211/291 [00:05<00:01, 41.49it/s]
Loading 0: 74%|███████▍ | 216/291 [00:05<00:01, 43.12it/s]
Loading 0: 76%|███████▌ | 221/291 [00:05<00:01, 36.51it/s]
Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 44.88it/s]
Loading 0: 81%|████████ | 235/291 [00:05<00:01, 41.62it/s]
Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 41.08it/s]
Loading 0: 85%|████████▍ | 246/291 [00:05<00:01, 44.73it/s]
Loading 0: 86%|████████▋ | 251/291 [00:06<00:00, 44.99it/s]
Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 44.43it/s]
Loading 0: 90%|█████████ | 262/291 [00:06<00:00, 41.54it/s]
Loading 0: 92%|█████████▏| 267/291 [00:06<00:00, 40.78it/s]
Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 44.89it/s]
Loading 0: 96%|█████████▌| 278/291 [00:06<00:00, 44.17it/s]
Loading 0: 97%|█████████▋| 283/291 [00:06<00:00, 36.49it/s]
Loading 0: 99%|█████████▊| 287/291 [00:12<00:01, 2.87it/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.
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: warnings.warn(
cgato-l3-1-thegreenlion-6585-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.
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: warnings.warn(
cgato-l3-1-thegreenlion-6585-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.
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: warnings.warn(
cgato-l3-1-thegreenlion-6585-v1-mkmlizer:
Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]
Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.37s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.99s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.19s/it]
cgato-l3-1-thegreenlion-6585-v1-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.44it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 4.03it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.67it/s]
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: Saving duration: 1.388s
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 15.673s
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-1-thegreenlion-6585-v1_reward
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-1-thegreenlion-6585-v1_reward/special_tokens_map.json
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-1-thegreenlion-6585-v1_reward/tokenizer_config.json
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-1-thegreenlion-6585-v1_reward/config.json
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-1-thegreenlion-6585-v1_reward/merges.txt
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-1-thegreenlion-6585-v1_reward/vocab.json
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-1-thegreenlion-6585-v1_reward/tokenizer.json
cgato-l3-1-thegreenlion-6585-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-1-thegreenlion-6585-v1_reward/reward.tensors
Job cgato-l3-1-thegreenlion-6585-v1-mkmlizer completed after 115.78s with status: succeeded
Stopping job with name cgato-l3-1-thegreenlion-6585-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-1-thegreenlion-6585-v1
Waiting for inference service cgato-l3-1-thegreenlion-6585-v1 to be ready
Inference service cgato-l3-1-thegreenlion-6585-v1 ready after 201.52689123153687s
Pipeline stage ISVCDeployer completed in 203.62s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.468907117843628s
Received healthy response to inference request in 1.3841516971588135s
Received healthy response to inference request in 1.3885700702667236s
Received healthy response to inference request in 1.3745167255401611s
Received healthy response to inference request in 1.3461365699768066s
5 requests
0 failed requests
5th percentile: 1.3518126010894775
10th percentile: 1.3574886322021484
20th percentile: 1.3688406944274902
30th percentile: 1.3764437198638917
40th percentile: 1.3802977085113526
50th percentile: 1.3841516971588135
60th percentile: 1.3859190464019775
70th percentile: 1.3876863956451415
80th percentile: 1.6046374797821046
90th percentile: 2.0367722988128665
95th percentile: 2.252839708328247
99th percentile: 2.4256936359405517
mean time: 1.5924564361572267
Pipeline stage StressChecker completed in 8.80s
cgato-l3-1-thegreenlion-_6585_v1 status is now deployed due to DeploymentManager action
cgato-l3-1-thegreenlion-_6585_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-1-thegreenlion-_6585_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-1-thegreenlion-6585-v1 is running
Tearing down inference service cgato-l3-1-thegreenlion-6585-v1
Service cgato-l3-1-thegreenlion-6585-v1 has been torndown
Pipeline stage ISVCDeleter completed in 8.10s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-1-thegreenlion-6585-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-1-thegreenlion-6585-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-1-thegreenlion-6585-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-1-thegreenlion-6585-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-1-thegreenlion-6585-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-1-thegreenlion-6585-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-1-thegreenlion-6585-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-1-thegreenlion-6585-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-1-thegreenlion-6585-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-1-thegreenlion-6585-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-1-thegreenlion-6585-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-1-thegreenlion-6585-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 9.12s
cgato-l3-1-thegreenlion-_6585_v1 status is now torndown due to DeploymentManager action