Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ Version: 0.9.7 ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: Downloaded to shared memory in 21.117s
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpme0jj9kc, device:0
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v85
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v85/config.json
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v85/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v85/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v85/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v85/flywheel_model.0.safetensors
Failed to get response for submission blend_nagok_2024-07-30: ('http://neversleep-noromaid-v0-8068-v140-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:47636->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: loading reward model from rirv938/retune_gpt2_xl_on_chaiml_sao10k_step_390
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:04<11:17, 2.34s/it]
Loading 0: 2%|▏ | 6/291 [00:04<02:59, 1.58it/s]
Loading 0: 4%|▍ | 13/291 [00:04<01:04, 4.33it/s]
Loading 0: 7%|▋ | 19/291 [00:05<00:37, 7.33it/s]
Loading 0: 8%|▊ | 24/291 [00:05<00:27, 9.88it/s]
Loading 0: 11%|█▏ | 33/291 [00:05<00:16, 16.05it/s]
Loading 0: 14%|█▍ | 42/291 [00:05<00:11, 22.41it/s]
Loading 0: 18%|█▊ | 51/291 [00:05<00:08, 28.35it/s]
Loading 0: 20%|██ | 59/291 [00:05<00:06, 35.40it/s]
Loading 0: 22%|██▏ | 65/291 [00:06<00:07, 29.18it/s]
Loading 0: 24%|██▍ | 70/291 [00:06<00:06, 31.78it/s]
Loading 0: 27%|██▋ | 78/291 [00:06<00:05, 35.95it/s]
Loading 0: 30%|██▉ | 86/291 [00:06<00:04, 43.64it/s]
Loading 0: 32%|███▏ | 92/291 [00:06<00:04, 42.86it/s]
Loading 0: 34%|███▎ | 98/291 [00:06<00:04, 45.39it/s]
Loading 0: 36%|███▌ | 105/291 [00:06<00:04, 44.38it/s]
Loading 0: 39%|███▉ | 113/291 [00:07<00:03, 51.55it/s]
Loading 0: 41%|████ | 119/291 [00:07<00:03, 49.04it/s]
Loading 0: 43%|████▎ | 125/291 [00:07<00:03, 50.95it/s]
Loading 0: 45%|████▌ | 132/291 [00:07<00:03, 47.56it/s]
Loading 0: 48%|████▊ | 140/291 [00:07<00:02, 55.05it/s]
Loading 0: 50%|█████ | 146/291 [00:07<00:02, 51.46it/s]
Loading 0: 52%|█████▏ | 152/291 [00:07<00:02, 52.86it/s]
Loading 0: 54%|█████▍ | 158/291 [00:07<00:02, 54.50it/s]
Loading 0: 56%|█████▋ | 164/291 [00:08<00:02, 49.73it/s]
Loading 0: 58%|█████▊ | 170/291 [00:08<00:03, 36.45it/s]
Loading 0: 60%|██████ | 176/291 [00:08<00:02, 41.17it/s]
Loading 0: 63%|██████▎ | 182/291 [00:08<00:02, 40.43it/s]
Loading 0: 64%|██████▍ | 187/291 [00:08<00:02, 41.39it/s]
Loading 0: 67%|██████▋ | 194/291 [00:08<00:02, 47.01it/s]
Loading 0: 69%|██████▊ | 200/291 [00:08<00:01, 45.79it/s]
Loading 0: 70%|███████ | 205/291 [00:09<00:01, 46.45it/s]
Loading 0: 73%|███████▎ | 212/291 [00:09<00:01, 52.25it/s]
Loading 0: 75%|███████▍ | 218/291 [00:09<00:01, 49.52it/s]
Loading 0: 77%|███████▋ | 224/291 [00:09<00:01, 51.19it/s]
Loading 0: 79%|███████▉ | 231/291 [00:09<00:01, 48.14it/s]
Loading 0: 82%|████████▏ | 239/291 [00:09<00:00, 55.23it/s]
Loading 0: 84%|████████▍ | 245/291 [00:09<00:00, 51.33it/s]
Loading 0: 86%|████████▋ | 251/291 [00:09<00:00, 52.17it/s]
Loading 0: 89%|████████▊ | 258/291 [00:10<00:00, 48.53it/s]
Loading 0: 91%|█████████▏| 266/291 [00:10<00:00, 39.72it/s]
Loading 0: 93%|█████████▎| 272/291 [00:10<00:00, 40.90it/s]
Loading 0: 95%|█████████▌| 277/291 [00:10<00:00, 42.57it/s]
Loading 0: 98%|█████████▊| 285/291 [00:10<00:00, 44.21it/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-v85-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v85-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-v85-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v85-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-v85-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: Saving duration: 1.362s
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: Processed model rirv938/retune_gpt2_xl_on_chaiml_sao10k_step_390 in 8.083s
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v85_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v85_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v85_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v85_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v85_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v85_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v85_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer completed after 85.07s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v85-mkmlizer
Pipeline stage MKMLizer completed in 86.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v85
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v85 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v85 ready after 133.18812084197998s
Pipeline stage ISVCDeployer completed in 134.88s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.072260856628418s
Received healthy response to inference request in 1.2038683891296387s
Received healthy response to inference request in 1.2388484477996826s
Received healthy response to inference request in 1.2595117092132568s
Received healthy response to inference request in 1.3731017112731934s
5 requests
0 failed requests
5th percentile: 1.2108644008636475
10th percentile: 1.2178604125976562
20th percentile: 1.2318524360656737
30th percentile: 1.2429811000823974
40th percentile: 1.251246404647827
50th percentile: 1.2595117092132568
60th percentile: 1.3049477100372315
70th percentile: 1.350383710861206
80th percentile: 1.5129335403442383
90th percentile: 1.7925971984863283
95th percentile: 1.932429027557373
99th percentile: 2.044294490814209
mean time: 1.429518222808838
Pipeline stage StressChecker completed in 7.83s
chaiml-sao10k-l3-rp-v3-3_v85 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v85 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v85
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v85 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v85
Service chaiml-sao10k-l3-rp-v3-3-v85 has been torndown
Pipeline stage ISVCDeleter completed in 4.98s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v85/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v85/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v85/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v85/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v85/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v85_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v85_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v85_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v85_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v85_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v85_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v85_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.54s
chaiml-sao10k-l3-rp-v3-3_v85 status is now torndown due to DeploymentManager action