developer_uid: chai_backend_admin
submission_id: chaiml-temp-reward-training_v1
model_name: chaiml-temp-reward-training_v1
model_group: ChaiML/temp_reward_train
status: inactive
timestamp: 2026-04-12T09:17:12+00:00
num_battles: 11136
num_wins: 4987
celo_rating: 1266.12
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/temp_reward_training
model_architecture: Glm4ForSequenceClassification
model_num_parameters: 32565331968.0
best_of: 1
max_input_tokens: 2048
max_output_tokens: 1
reward_model: default
display_name: chaiml-temp-reward-training_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/temp_reward_training
model_size: 33B
ranking_group: single
us_pacific_date: 2026-04-12
win_ratio: 0.44782686781609193
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': ['\n'], 'max_input_tokens': 2048, 'best_of': 1, 'max_output_tokens': 1}
formatter: {'memory_template': "[gMASK]<sop><|system|>\n{bot_name}'s persona:", 'prompt_template': ' {memory}', 'bot_template': '<|assistant|>\n{message}', 'user_template': '<|user|>\n{message}', 'response_template': '', '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-temp-reward-training-v1-uploader
Waiting for job on chaiml-temp-reward-training-v1-uploader to finish
chaiml-temp-reward-training-v1-uploader: Using quantization_mode: none
chaiml-temp-reward-training-v1-uploader: Downloading snapshot of ChaiML/temp_reward_training...
2026-04-12T06:34:10.529892+00:00 monitor updated for chaiml-temp-reward-training_v1
chaiml-temp-reward-training-v1-uploader: Downloaded in 52.928s
chaiml-temp-reward-training-v1-uploader: Processed model ChaiML/temp_reward_training in 53.043s
chaiml-temp-reward-training-v1-uploader: creating bucket guanaco-vllm-models
chaiml-temp-reward-training-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-temp-reward-training-v1-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-temp-reward-training-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-temp-reward-training-v1-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-temp-reward-training-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-temp-reward-training-v1-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-temp-reward-training-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-temp-reward-training-v1-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-temp-reward-training-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-temp-reward-training-v1-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-temp-reward-training-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-temp-reward-training-v1-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-temp-reward-training-v1-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-temp-reward-training-v1-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-temp-reward-training-v1-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-temp-reward-training-v1-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-temp-reward-training-v1-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-temp-reward-training-v1-uploader: uploading /tmp/model_output to s3://guanaco-vllm-models/chaiml-temp-reward-training-v1/default
chaiml-temp-reward-training-v1-uploader: cp /tmp/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-temp-reward-training-v1/default/model.safetensors.index.json
chaiml-temp-reward-training-v1-uploader: cp /tmp/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-temp-reward-training-v1/default/chat_template.jinja
chaiml-temp-reward-training-v1-uploader: cp /tmp/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-temp-reward-training-v1/default/.gitattributes
chaiml-temp-reward-training-v1-uploader: cp /tmp/model_output/training_args.bin s3://guanaco-vllm-models/chaiml-temp-reward-training-v1/default/training_args.bin
chaiml-temp-reward-training-v1-uploader: cp /tmp/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-temp-reward-training-v1/default/tokenizer_config.json
chaiml-temp-reward-training-v1-uploader: cp /tmp/model_output/config.json s3://guanaco-vllm-models/chaiml-temp-reward-training-v1/default/config.json
chaiml-temp-reward-training-v1-uploader: cp /tmp/model_output/README.md s3://guanaco-vllm-models/chaiml-temp-reward-training-v1/default/README.md
chaiml-temp-reward-training-v1-uploader: cp /tmp/model_output/model.safetensors s3://guanaco-vllm-models/chaiml-temp-reward-training-v1/default/model.safetensors
chaiml-temp-reward-training-v1-uploader: cp /tmp/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-temp-reward-training-v1/default/tokenizer.json
chaiml-temp-reward-training-v1-uploader: cp /tmp/model_output/model-00002-of-00002.safetensors s3://guanaco-vllm-models/chaiml-temp-reward-training-v1/default/model-00002-of-00002.safetensors
2026-04-12T06:35:10.648266+00:00 monitor updated for chaiml-temp-reward-training_v1
chaiml-temp-reward-training-v1-uploader: cp /tmp/model_output/model-00001-of-00002.safetensors s3://guanaco-vllm-models/chaiml-temp-reward-training-v1/default/model-00001-of-00002.safetensors
Job chaiml-temp-reward-training-v1-uploader completed after 164.74s with status: succeeded
Stopping job with name chaiml-temp-reward-training-v1-uploader
Pipeline stage VLLMUploader completed in 165.16s
run pipeline stage %s
Running pipeline stage VLLMUploaderAMD
Pipeline stage vllm_upload_amd skipped, reason=not amd cluster
Pipeline stage VLLMUploaderAMD completed in 0.08s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 1.96s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-temp-reward-training-v1
Waiting for inference service chaiml-temp-reward-training-v1 to be ready
2026-04-12T06:36:10.739361+00:00 monitor updated for chaiml-temp-reward-training_v1
2026-04-12T06:37:10.827854+00:00 monitor updated for chaiml-temp-reward-training_v1
2026-04-12T06:38:10.920011+00:00 monitor updated for chaiml-temp-reward-training_v1
Inference service chaiml-temp-reward-training-v1 ready after 170.54922246932983s
Pipeline stage VLLMDeployer completed in 171.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.056879758834839s
Received healthy response to inference request in 5.100656032562256s
Received healthy response to inference request in 10.50673246383667s
2026-04-12T06:39:11.002716+00:00 monitor updated for chaiml-temp-reward-training_v1
Received healthy response to inference request in 3.080819845199585s
Received healthy response to inference request in 2.577300548553467s
5 requests
0 failed requests
5th percentile: 2.6780044078826903
10th percentile: 2.778708267211914
20th percentile: 2.9801159858703614
30th percentile: 3.4760318279266356
40th percentile: 4.266455793380738
50th percentile: 5.056879758834839
60th percentile: 5.074390268325805
70th percentile: 5.091900777816773
80th percentile: 6.18187131881714
90th percentile: 8.344301891326905
95th percentile: 9.425517177581787
99th percentile: 10.290489406585694
mean time: 5.264477729797363
Pipeline stage StressChecker completed in 28.63s
Shutdown handler de-registered
chaiml-temp-reward-training_v1 status is now deployed due to DeploymentManager action
chaiml-temp-reward-training_v1 status is now inactive due to auto deactivation removed underperforming models