chaiml-grpo-q235b-kimid_83709

developer_uid: chai_backend_admin
submission_id: chaiml-grpo-q235b-kimid_83709_v3
model_name: chaiml-grpo-q235b-kimid_83709_v3
model_group: ChaiML/grpo-q235b-kimid-
status: deployed
timestamp: 2026-03-02T18:26:03+00:00
num_battles: 11782
num_wins: 6272
celo_rating: 1318.51
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/grpo-q235b-kimid-v5a-merged-chai-rm-step-450
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-grpo-q235b-kimid_83709_v3
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/grpo-q235b-kimid-v5a-merged-chai-rm-step-450
model_size: 19B
ranking_group: single
us_pacific_date: 2026-03-02
win_ratio: 0.5323374639280258
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>', '</s>', '####', '<|user|>', '<|im_end|>', '<|assistant|>'], '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-grpo-q235b-kimid-83709-v3-uploader
Waiting for job on chaiml-grpo-q235b-kimid-83709-v3-uploader to finish
chaiml-grpo-q235b-kimid-83709-v3-uploader: Using quantization_mode: w4a16
chaiml-grpo-q235b-kimid-83709-v3-uploader: Checking if ChaiML/grpo-q235b-kimid-v5a-merged-chai-rm-step-450-W4A16 already exists in ChaiML
chaiml-grpo-q235b-kimid-83709-v3-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-grpo-q235b-kimid-83709-v3-uploader: Downloading snapshot of ChaiML/grpo-q235b-kimid-v5a-merged-chai-rm-step-450-W4A16...
chaiml-grpo-q235b-kimid-83709-v3-uploader: Downloaded in 58.614s
chaiml-grpo-q235b-kimid-83709-v3-uploader: Processed model ChaiML/grpo-q235b-kimid-v5a-merged-chai-rm-step-450 in 59.159s
chaiml-grpo-q235b-kimid-83709-v3-uploader: creating bucket guanaco-vllm-models
chaiml-grpo-q235b-kimid-83709-v3-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-kimid-83709-v3-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-grpo-q235b-kimid-83709-v3-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-grpo-q235b-kimid-83709-v3-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-grpo-q235b-kimid-83709-v3-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-kimid-83709-v3-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-grpo-q235b-kimid-83709-v3-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-kimid-83709-v3-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-grpo-q235b-kimid-83709-v3-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-kimid-83709-v3-uploader:   if re.search("-\.", bucket, re.UNICODE):
chaiml-grpo-q235b-kimid-83709-v3-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-kimid-83709-v3-uploader:   if re.search("\.\.", bucket, re.UNICODE):
chaiml-grpo-q235b-kimid-83709-v3-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-grpo-q235b-kimid-83709-v3-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-grpo-q235b-kimid-83709-v3-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-grpo-q235b-kimid-83709-v3-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-grpo-q235b-kimid-83709-v3-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-grpo-q235b-kimid-83709-v3-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/added_tokens.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/added_tokens.json
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/tokenizer_config.json
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/config.json
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/.gitattributes
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/chat_template.jinja
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/generation_config.json
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/merges.txt
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/quantization_config.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/quantization_config.json
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/special_tokens_map.json
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/vocab.json
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/tokenizer.json
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model.safetensors.index.json
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00027-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00027-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00004-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00004-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00017-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00017-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00003-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00003-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00008-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00008-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00009-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00009-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00007-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00007-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00021-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00021-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00011-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00011-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00012-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00012-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00023-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00023-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00022-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00022-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00026-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00026-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00024-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00024-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00001-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00001-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00013-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00013-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00025-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00025-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00002-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00002-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00019-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00019-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00020-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00020-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00016-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00016-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00006-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00006-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00010-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00010-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00015-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00015-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00018-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00018-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00005-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00005-of-00027.safetensors
chaiml-grpo-q235b-kimid-83709-v3-uploader: cp /dev/shm/model_output/model-00014-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-83709-v3/default/model-00014-of-00027.safetensors
Job chaiml-grpo-q235b-kimid-83709-v3-uploader completed after 145.12s with status: succeeded
Stopping job with name chaiml-grpo-q235b-kimid-83709-v3-uploader
Pipeline stage VLLMUploader completed in 145.87s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.48s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-grpo-q235b-kimid-83709-v3
Waiting for inference service chaiml-grpo-q235b-kimid-83709-v3 to be ready
Inference service chaiml-grpo-q235b-kimid-83709-v3 ready after 381.3909797668457s
Pipeline stage VLLMDeployer completed in 381.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0692763328552246s
Received healthy response to inference request in 2.1231203079223633s
Received healthy response to inference request in 2.109299898147583s
Received healthy response to inference request in 2.1317331790924072s
Received healthy response to inference request in 2.200920581817627s
Received healthy response to inference request in 1.9942388534545898s
Received healthy response to inference request in 1.8559954166412354s
Received healthy response to inference request in 1.928403615951538s
Received healthy response to inference request in 2.0884010791778564s
Received healthy response to inference request in 1.897920846939087s
Received healthy response to inference request in 2.0927979946136475s
Received healthy response to inference request in 2.185314178466797s
Received healthy response to inference request in 1.932812213897705s
Received healthy response to inference request in 2.002631664276123s
Received healthy response to inference request in 2.1290037631988525s
Received healthy response to inference request in 2.0006699562072754s
Received healthy response to inference request in 2.0007035732269287s
Received healthy response to inference request in 2.1433358192443848s
Received healthy response to inference request in 2.0497689247131348s
Received healthy response to inference request in 2.0169453620910645s
Received healthy response to inference request in 2.030852794647217s
Received healthy response to inference request in 2.1728250980377197s
Received healthy response to inference request in 2.1845462322235107s
Received healthy response to inference request in 2.198664426803589s
Received healthy response to inference request in 2.107991933822632s
Received healthy response to inference request in 2.1570661067962646s
Received healthy response to inference request in 2.2213737964630127s
Received healthy response to inference request in 2.106616735458374s
Received healthy response to inference request in 2.0324039459228516s
Received healthy response to inference request in 1.9419763088226318s
30 requests
0 failed requests
5th percentile: 1.91163809299469
10th percentile: 1.9323713541030885
20th percentile: 1.9993837356567383
30th percentile: 2.012651252746582
40th percentile: 2.0428229331970216
50th percentile: 2.090599536895752
60th percentile: 2.1085151195526124
70th percentile: 2.129822587966919
80th percentile: 2.1602179050445556
90th percentile: 2.186649203300476
95th percentile: 2.19990531206131
99th percentile: 2.2154423642158507
mean time: 2.0702536980311077
Pipeline stage StressChecker completed in 66.92s
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 0.67s
Shutdown handler de-registered
chaiml-grpo-q235b-kimid_83709_v3 status is now deployed due to DeploymentManager action
chaiml-grpo-q235b-kimid_83709_v3 status is now inactive due to system request