chaiml-grpo-q235b-kimid_35892

developer_uid: acehao-chai
submission_id: chaiml-grpo-q235b-kimid_35892_v2
model_name: chaiml-grpo-q235b-kimid_35892_v2
model_group: ChaiML/grpo-q235b-kimid-
status: torndown
timestamp: 2026-03-11T17:33:25+00:00
num_battles: 10368
num_wins: 5690
celo_rating: 1330.9
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-800
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_35892_v2
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/grpo-q235b-kimid-v5a-merged-chai-rm-step-800
model_size: 19B
ranking_group: single
us_pacific_date: 2026-02-19
win_ratio: 0.548804012345679
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': ['<|assistant|>', '<|im_end|>', '####', '<|user|>', '</think>', '</s>'], '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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Running pipeline stage VLLMUploader
Starting job with name chaiml-grpo-q235b-kimid-35892-v2-uploader
Waiting for job on chaiml-grpo-q235b-kimid-35892-v2-uploader to finish
Failed to get response for submission chaiml-grpo-q235b-kimid_37540_v1: HTTPConnectionPool(host='chaiml-grpo-q235b-kimid-37540-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-grpo-q235b-kimid-35892-v2-uploader: Using quantization_mode: w4a16
chaiml-grpo-q235b-kimid-35892-v2-uploader: Checking if ChaiML/grpo-q235b-kimid-v5a-merged-chai-rm-step-800-W4A16 already exists in ChaiML
chaiml-grpo-q235b-kimid-35892-v2-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-grpo-q235b-kimid-35892-v2-uploader: Downloading snapshot of ChaiML/grpo-q235b-kimid-v5a-merged-chai-rm-step-800-W4A16...
chaiml-grpo-q235b-kimid-35892-v2-uploader: Downloaded in 51.706s
chaiml-grpo-q235b-kimid-35892-v2-uploader: Processed model ChaiML/grpo-q235b-kimid-v5a-merged-chai-rm-step-800 in 52.278s
chaiml-grpo-q235b-kimid-35892-v2-uploader: creating bucket guanaco-vllm-models
chaiml-grpo-q235b-kimid-35892-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-kimid-35892-v2-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-grpo-q235b-kimid-35892-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-grpo-q235b-kimid-35892-v2-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-grpo-q235b-kimid-35892-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-kimid-35892-v2-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-grpo-q235b-kimid-35892-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-kimid-35892-v2-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-grpo-q235b-kimid-35892-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-kimid-35892-v2-uploader:   if re.search("-\.", bucket, re.UNICODE):
chaiml-grpo-q235b-kimid-35892-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-kimid-35892-v2-uploader:   if re.search("\.\.", bucket, re.UNICODE):
chaiml-grpo-q235b-kimid-35892-v2-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-grpo-q235b-kimid-35892-v2-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-grpo-q235b-kimid-35892-v2-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-grpo-q235b-kimid-35892-v2-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-grpo-q235b-kimid-35892-v2-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-grpo-q235b-kimid-35892-v2-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/.gitattributes
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/chat_template.jinja
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/generation_config.json
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/config.json
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/tokenizer_config.json
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/special_tokens_map.json
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/merges.txt
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/added_tokens.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/added_tokens.json
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/quantization_config.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/quantization_config.json
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/vocab.json
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model.safetensors.index.json
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/tokenizer.json
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00027-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00027-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00011-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00011-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00019-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00019-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00010-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00010-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00004-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00004-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00021-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00021-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00024-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00024-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00022-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00022-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00002-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00002-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00001-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00001-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00012-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00012-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00015-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00015-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00007-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00007-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00017-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00017-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00013-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00013-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00014-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00014-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00008-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00008-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00025-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00025-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00003-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00003-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00009-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00009-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00026-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00026-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00020-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00020-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00018-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00018-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00016-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00016-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00006-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00006-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00023-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00023-of-00027.safetensors
chaiml-grpo-q235b-kimid-35892-v2-uploader: cp /dev/shm/model_output/model-00005-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-kimid-35892-v2/default/model-00005-of-00027.safetensors
Job chaiml-grpo-q235b-kimid-35892-v2-uploader completed after 135.39s with status: succeeded
Stopping job with name chaiml-grpo-q235b-kimid-35892-v2-uploader
Pipeline stage VLLMUploader completed in 136.34s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-grpo-q235b-kimid-35892-v2
Waiting for inference service chaiml-grpo-q235b-kimid-35892-v2 to be ready
Failed to get response for submission chaiml-mistral-24b-2048_15988_v1: ('http://chaiml-mistral-24b-2048-15988-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-mistral-24b-2048_15988_v1: ('http://chaiml-mistral-24b-2048-15988-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-mistral-24b-2048_54327_v6: ('http://chaiml-mistral-24b-2048-54327-v6-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-mistral-24b-2048_15988_v1: ('http://chaiml-mistral-24b-2048-15988-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-grpo-q235b-kimid_37540_v1: HTTPConnectionPool(host='chaiml-grpo-q235b-kimid-37540-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-grpo-q235b-kimid-35892-v2 ready after 382.07693552970886s
Pipeline stage VLLMDeployer completed in 382.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.978297472000122s
Received healthy response to inference request in 1.9324676990509033s
Received healthy response to inference request in 1.7670512199401855s
Received healthy response to inference request in 1.987020492553711s
Received healthy response to inference request in 2.163681983947754s
Received healthy response to inference request in 1.9197099208831787s
Received healthy response to inference request in 2.0135514736175537s
Received healthy response to inference request in 1.9012055397033691s
Received healthy response to inference request in 2.2253265380859375s
Received healthy response to inference request in 2.0647971630096436s
Received healthy response to inference request in 2.4464476108551025s
Received healthy response to inference request in 2.1230154037475586s
Received healthy response to inference request in 1.9650557041168213s
Received healthy response to inference request in 1.8736987113952637s
Received healthy response to inference request in 1.9911978244781494s
Received healthy response to inference request in 1.9691364765167236s
Received healthy response to inference request in 1.9460079669952393s
Received healthy response to inference request in 2.0152618885040283s
Received healthy response to inference request in 1.9582328796386719s
Received healthy response to inference request in 2.1055104732513428s
Received healthy response to inference request in 2.3026816844940186s
Received healthy response to inference request in 1.7180390357971191s
Received healthy response to inference request in 1.8968243598937988s
Received healthy response to inference request in 2.577855110168457s
Received healthy response to inference request in 2.165621042251587s
Received healthy response to inference request in 2.1609537601470947s
Received healthy response to inference request in 2.002073287963867s
Received healthy response to inference request in 2.1528689861297607s
Received healthy response to inference request in 1.8950035572052002s
Received healthy response to inference request in 2.0821545124053955s
30 requests
0 failed requests
5th percentile: 1.8150425910949708
10th percentile: 1.8928730726242065
20th percentile: 1.9160090446472169
30th percentile: 1.954565405845642
40th percentile: 1.9746330738067628
50th percentile: 1.9966355562210083
60th percentile: 2.0350759983062745
70th percentile: 2.1107619524002073
80th percentile: 2.1614994049072265
90th percentile: 2.2330620527267455
95th percentile: 2.3817529439926144
99th percentile: 2.5397469353675843
mean time: 2.043358325958252
Pipeline stage StressChecker completed in 65.19s
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 0.70s
Shutdown handler de-registered
chaiml-grpo-q235b-kimid_35892_v2 status is now deployed due to DeploymentManager action
chaiml-grpo-q235b-kimid_35892_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-grpo-q235b-kimid_35892_v2 status is now inactive due to Froze recruitment for AB test 0220_feynman
Pipeline stage VLLMModelDeleter completed in 56.28s
Shutdown handler de-registered
chaiml-grpo-q235b-kimid_35892_v2 status is now torndown due to DeploymentManager action
Deleting key chaiml-grpo-q235b-opusd-35623-v1/default/vocab.json from bucket guanaco-vllm-models
Shutdown handler de-registered