developer_uid: rirv938
submission_id: chaiml-q235b-judge-dpo-_18429_v2
model_name: chaiml-q235b-judge-dpo-_18429_v2
model_group: ChaiML/q235b_judge_dpo_l
status: torndown
timestamp: 2026-04-02T20:52:26+00:00
num_battles: 10353
num_wins: 5342
celo_rating: 1322.79
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/q235b_judge_dpo_lr1-step450-merged
model_architecture: Qwen3MoeForCausalLM
model_num_parameters: 18790207488.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 80
reward_model: default
display_name: chaiml-q235b-judge-dpo-_18429_v2
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/q235b_judge_dpo_lr1-step450-merged
model_size: 19B
ranking_group: single
us_pacific_date: 2026-03-30
win_ratio: 0.5159857046266783
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</think>', '<|assistant|>', '</s>', '####', '<|im_end|>', '<|user|>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 80}
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s persona: {memory}<|im_end|>\n", 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}
Resubmit model
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-q235b-judge-dpo-18429-v2-uploader
Waiting for job on chaiml-q235b-judge-dpo-18429-v2-uploader to finish
chaiml-q235b-judge-dpo-18429-v2-uploader: Using quantization_mode: w4a16
chaiml-q235b-judge-dpo-18429-v2-uploader: Checking if ChaiML/q235b_judge_dpo_lr1-step450-merged-W4A16 already exists in ChaiML
chaiml-q235b-judge-dpo-18429-v2-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-q235b-judge-dpo-18429-v2-uploader: Downloading snapshot of ChaiML/q235b_judge_dpo_lr1-step450-merged-W4A16...
2026-03-30T16:29:22.399069+00:00 monitor updated for chaiml-q235b-judge-dpo-_18429_v2
chaiml-q235b-judge-dpo-18429-v2-uploader: Downloaded in 62.938s
chaiml-q235b-judge-dpo-18429-v2-uploader: Processed model ChaiML/q235b_judge_dpo_lr1-step450-merged in 63.484s
chaiml-q235b-judge-dpo-18429-v2-uploader: creating bucket guanaco-vllm-models
chaiml-q235b-judge-dpo-18429-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-judge-dpo-18429-v2-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-q235b-judge-dpo-18429-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-q235b-judge-dpo-18429-v2-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-q235b-judge-dpo-18429-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-judge-dpo-18429-v2-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-q235b-judge-dpo-18429-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-judge-dpo-18429-v2-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-q235b-judge-dpo-18429-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-judge-dpo-18429-v2-uploader:   if re.search("-\.", bucket, re.UNICODE):
chaiml-q235b-judge-dpo-18429-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-judge-dpo-18429-v2-uploader:   if re.search("\.\.", bucket, re.UNICODE):
chaiml-q235b-judge-dpo-18429-v2-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-q235b-judge-dpo-18429-v2-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-q235b-judge-dpo-18429-v2-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-q235b-judge-dpo-18429-v2-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-q235b-judge-dpo-18429-v2-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-q235b-judge-dpo-18429-v2-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/.gitattributes
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/quantization_config.json s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/quantization_config.json
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/special_tokens_map.json
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/added_tokens.json s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/added_tokens.json
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/tokenizer_config.json
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/config.json
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/merges.txt
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/generation_config.json
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/chat_template.jinja
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/vocab.json
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model.safetensors.index.json
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/tokenizer.json
2026-03-30T16:30:22.830690+00:00 monitor updated for chaiml-q235b-judge-dpo-_18429_v2
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00027-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00027-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00013-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00013-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00002-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00002-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00010-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00010-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00024-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00024-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00022-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00022-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00005-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00005-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00011-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00011-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00008-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00008-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00012-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00012-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00023-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00023-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00021-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00021-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00001-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00001-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00025-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00025-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00006-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00006-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00014-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00014-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00020-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00020-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00003-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00003-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00009-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00009-of-00027.safetensors
chaiml-q235b-judge-dpo-18429-v2-uploader: cp /dev/shm/model_output/model-00018-of-00027.safetensors s3://guanaco-vllm-models/chaiml-q235b-judge-dpo-18429-v2/default/model-00018-of-00027.safetensors
Job chaiml-q235b-judge-dpo-18429-v2-uploader completed after 156.79s with status: succeeded
Stopping job with name chaiml-q235b-judge-dpo-18429-v2-uploader
Pipeline stage VLLMUploader completed in 157.53s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 2.68s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-q235b-judge-dpo-18429-v2
Waiting for inference service chaiml-q235b-judge-dpo-18429-v2 to be ready
2026-03-30T16:31:23.219043+00:00 monitor updated for chaiml-q235b-judge-dpo-_18429_v2
2026-03-30T16:32:23.427732+00:00 monitor updated for chaiml-q235b-judge-dpo-_18429_v2
2026-03-30T16:33:23.627787+00:00 monitor updated for chaiml-q235b-judge-dpo-_18429_v2
2026-03-30T16:34:23.805979+00:00 monitor updated for chaiml-q235b-judge-dpo-_18429_v2
Inference service chaiml-q235b-judge-dpo-18429-v2 ready after 210.6159279346466s
Pipeline stage VLLMDeployer completed in 211.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.024046182632446s
Received healthy response to inference request in 3.425809383392334s
Received healthy response to inference request in 1.631279468536377s
Received healthy response to inference request in 3.4331791400909424s
Received healthy response to inference request in 1.5529310703277588s
Received healthy response to inference request in 1.432697057723999s
Received healthy response to inference request in 1.561218500137329s
Received healthy response to inference request in 1.4479236602783203s
Received healthy response to inference request in 1.4262502193450928s
Received healthy response to inference request in 1.4538600444793701s
Received healthy response to inference request in 3.5244054794311523s
Received healthy response to inference request in 1.4540369510650635s
Received healthy response to inference request in 1.4974870681762695s
Received healthy response to inference request in 1.4475791454315186s
Received healthy response to inference request in 1.4973843097686768s
Received healthy response to inference request in 1.567711353302002s
Received healthy response to inference request in 1.5585336685180664s
Received healthy response to inference request in 1.5409839153289795s
Received healthy response to inference request in 1.452535629272461s
Received healthy response to inference request in 1.4848058223724365s
Received healthy response to inference request in 1.4480926990509033s
Received healthy response to inference request in 3.4928431510925293s
Received healthy response to inference request in 1.4863612651824951s
Received healthy response to inference request in 1.4573588371276855s
2026-03-30T16:35:23.997464+00:00 monitor updated for chaiml-q235b-judge-dpo-_18429_v2
Received healthy response to inference request in 1.5089268684387207s
Received healthy response to inference request in 1.50187087059021s
Received healthy response to inference request in 1.6751983165740967s
Received healthy response to inference request in 1.523190975189209s
Received healthy response to inference request in 1.5193116664886475s
Received healthy response to inference request in 1.563835859298706s
30 requests
0 failed requests
5th percentile: 1.4393939971923828
10th percentile: 1.4478892087936401
20th percentile: 1.4535951614379883
30th percentile: 1.4765717267990113
40th percentile: 1.4974459648132323
50th percentile: 1.514119267463684
60th percentile: 1.5457627773284912
70th percentile: 1.5620037078857423
80th percentile: 1.640063238143921
90th percentile: 3.439145541191101
95th percentile: 3.510202431678772
99th percentile: 3.8791503787040713
mean time: 1.85305495262146
Pipeline stage StressChecker completed in 59.98s
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 1.44s
Shutdown handler de-registered
chaiml-q235b-judge-dpo-_18429_v2 status is now deployed due to DeploymentManager action
chaiml-q235b-judge-dpo-_18429_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-q235b-judge-dpo-_18429_v2 status is now torndown due to DeploymentManager action