Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMUploader
Starting job with name chaiml-qwen-bobo-dpo-ju-40611-v1-uploader
Waiting for job on chaiml-qwen-bobo-dpo-ju-40611-v1-uploader to finish
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: Using quantization_mode: none
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: Downloading snapshot of ChaiML/qwen_bobo_dpo_judge_plus_reward_700_much_safer_merged...
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: Downloaded in 31.565s
2026-03-28T17:06:52.887716+00:00 monitor updated for chaiml-qwen-bobo-dpo-ju_40611_v1
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: Processed model ChaiML/qwen_bobo_dpo_judge_plus_reward_700_much_safer_merged in 51.780s
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: creating bucket guanaco-vllm-models
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-qwen-bobo-dpo-ju-40611-v1/default
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-qwen-bobo-dpo-ju-40611-v1/default/.gitattributes
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-qwen-bobo-dpo-ju-40611-v1/default/tokenizer_config.json
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-qwen-bobo-dpo-ju-40611-v1/default/config.json
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-qwen-bobo-dpo-ju-40611-v1/default/generation_config.json
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/chaiml-qwen-bobo-dpo-ju-40611-v1/default/README.md
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-qwen-bobo-dpo-ju-40611-v1/default/model.safetensors.index.json
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-qwen-bobo-dpo-ju-40611-v1/default/chat_template.jinja
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-qwen-bobo-dpo-ju-40611-v1/default/tokenizer.json
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: cp /dev/shm/model_output/model-00002-of-00002.safetensors s3://guanaco-vllm-models/chaiml-qwen-bobo-dpo-ju-40611-v1/default/model-00002-of-00002.safetensors
2026-03-28T17:07:52.977194+00:00 monitor updated for chaiml-qwen-bobo-dpo-ju_40611_v1
chaiml-qwen-bobo-dpo-ju-40611-v1-uploader: cp /dev/shm/model_output/model-00001-of-00002.safetensors s3://guanaco-vllm-models/chaiml-qwen-bobo-dpo-ju-40611-v1/default/model-00001-of-00002.safetensors
Job chaiml-qwen-bobo-dpo-ju-40611-v1-uploader completed after 163.07s with status: succeeded
Stopping job with name chaiml-qwen-bobo-dpo-ju-40611-v1-uploader
Pipeline stage VLLMUploader completed in 163.56s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.33s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-qwen-bobo-dpo-ju-40611-v1
Waiting for inference service chaiml-qwen-bobo-dpo-ju-40611-v1 to be ready
2026-03-28T17:08:53.072098+00:00 monitor updated for chaiml-qwen-bobo-dpo-ju_40611_v1
2026-03-28T17:09:53.164700+00:00 monitor updated for chaiml-qwen-bobo-dpo-ju_40611_v1
2026-03-28T17:10:53.257436+00:00 monitor updated for chaiml-qwen-bobo-dpo-ju_40611_v1
Inference service chaiml-qwen-bobo-dpo-ju-40611-v1 ready after 170.4028537273407s
Pipeline stage VLLMDeployer completed in 170.94s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-28T17:11:53.350314+00:00 monitor updated for chaiml-qwen-bobo-dpo-ju_40611_v1
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-28T17:12:53.442740+00:00 monitor updated for chaiml-qwen-bobo-dpo-ju_40611_v1
Received healthy response to inference request in 17.20016574859619s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.6253561973571777s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-28T17:13:53.542960+00:00 monitor updated for chaiml-qwen-bobo-dpo-ju_40611_v1
Received healthy response to inference request in 9.289398431777954s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-28T17:14:53.635570+00:00 monitor updated for chaiml-qwen-bobo-dpo-ju_40611_v1
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.015684127807617s
Received healthy response to inference request in 2.634828567504883s
Received healthy response to inference request in 2.73913836479187s
Received healthy response to inference request in 2.8555312156677246s
Received healthy response to inference request in 2.658561944961548s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.6236884593963623s
Received healthy response to inference request in 2.7353639602661133s
2026-03-28T17:15:53.733748+00:00 monitor updated for chaiml-qwen-bobo-dpo-ju_40611_v1
Received healthy response to inference request in 17.858922004699707s
Received healthy response to inference request in 2.738687038421631s
Received healthy response to inference request in 2.5037195682525635s
Received healthy response to inference request in 2.970780611038208s
Received healthy response to inference request in 2.716303586959839s
Received healthy response to inference request in 2.7510218620300293s
Received healthy response to inference request in 2.619446039199829s
Received healthy response to inference request in 2.6856565475463867s
Received healthy response to inference request in 2.590531587600708s
Received healthy response to inference request in 2.5800113677978516s
30 requests
10 failed requests
5th percentile: 2.584745466709137
10th percentile: 2.616554594039917
20th percentile: 2.632934093475342
30th percentile: 2.707109475135803
40th percentile: 2.7389578342437746
50th percentile: 2.9131559133529663
60th percentile: 12.453705358505237
70th percentile: 20.113126230239867
80th percentile: 20.124212217330932
90th percentile: 20.131192803382874
95th percentile: 20.142211771011354
99th percentile: 20.213879079818724
mean time: 9.725833249092101
%s, retrying in %s seconds...
Received healthy response to inference request in 2.445085048675537s
Received healthy response to inference request in 2.673625946044922s
Received healthy response to inference request in 2.4058430194854736s
Received healthy response to inference request in 2.556879758834839s
Received healthy response to inference request in 2.717453718185425s
Received healthy response to inference request in 2.399775743484497s
Received healthy response to inference request in 2.508645534515381s
Received healthy response to inference request in 2.6092052459716797s
Received healthy response to inference request in 2.4913811683654785s
Received healthy response to inference request in 2.7172508239746094s
Received healthy response to inference request in 2.434175968170166s
Received healthy response to inference request in 2.518939971923828s
2026-03-28T17:16:53.832239+00:00 monitor updated for chaiml-qwen-bobo-dpo-ju_40611_v1
Received healthy response to inference request in 2.6372852325439453s
Received healthy response to inference request in 3.3363990783691406s
Received healthy response to inference request in 2.538829803466797s
Received healthy response to inference request in 2.9813125133514404s
Received healthy response to inference request in 2.5414891242980957s
Received healthy response to inference request in 2.5936622619628906s
Received healthy response to inference request in 2.6420252323150635s
Received healthy response to inference request in 2.61293625831604s
Received healthy response to inference request in 2.4954769611358643s
Received healthy response to inference request in 2.636295795440674s
Received healthy response to inference request in 2.55892276763916s
Received healthy response to inference request in 2.656344413757324s
Received healthy response to inference request in 3.214512825012207s
Received healthy response to inference request in 2.6332366466522217s
Received healthy response to inference request in 2.697781801223755s
Received healthy response to inference request in 2.6616532802581787s
Received healthy response to inference request in 2.6663761138916016s
Received healthy response to inference request in 2.6244516372680664s
30 requests
0 failed requests
5th percentile: 2.4185928463935853
10th percentile: 2.443994140625
20th percentile: 2.5060118198394776
30th percentile: 2.5406913280487062
40th percentile: 2.5797664642333986
50th percentile: 2.6186939477920532
60th percentile: 2.6366915702819824
70th percentile: 2.6579370737075805
80th percentile: 2.6784571170806886
90th percentile: 2.743839597702027
95th percentile: 3.1095726847648613
99th percentile: 3.30105206489563
mean time: 2.64024178981781
Pipeline stage StressChecker completed in 375.83s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.68s
Shutdown handler de-registered
chaiml-qwen-bobo-dpo-ju_40611_v1 status is now deployed due to DeploymentManager action