chaiml-grpo-q235b-opusd_55346

developer_uid: acehao-chai

submission_id: chaiml-grpo-q235b-opusd_55346_v2

model_name: chaiml-grpo-q235b-opusd_55346_v2

model_group: ChaiML/grpo-q235b-opusd-

status: torndown

timestamp: 2026-02-22T19:42:02+00:00

num_battles: 11131

num_wins: 891

celo_rating: 867.31

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/grpo-q235b-opusd-v1-merged-chai-rm-high-kl-averaged-models

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-opusd_55346_v2

ineligible_reason: max_output_tokens!=64

is_internal_developer: False

language_model: ChaiML/grpo-q235b-opusd-v1-merged-chai-rm-high-kl-averaged-models

model_size: 19B

ranking_group: single

us_pacific_date: 2026-02-19

win_ratio: 0.08004671637768394

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
Running pipeline stage VLLMUploader
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Starting job with name chaiml-grpo-q235b-opusd-55346-v2-uploader
Waiting for job on chaiml-grpo-q235b-opusd-55346-v2-uploader to finish
chaiml-grpo-q235b-opusd-55346-v2-uploader: Using quantization_mode: w4a16
chaiml-grpo-q235b-opusd-55346-v2-uploader: Checking if ChaiML/grpo-q235b-opusd-v1-merged-chai-rm-high-kl-averaged-models-W4A16 already exists in ChaiML
chaiml-grpo-q235b-opusd-55346-v2-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-grpo-q235b-opusd-55346-v2-uploader: Downloading snapshot of ChaiML/grpo-q235b-opusd-v1-merged-chai-rm-high-kl-averaged-models-W4A16...
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-opusd-55346-v2-uploader: Downloaded in 55.043s
chaiml-grpo-q235b-opusd-55346-v2-uploader: Processed model ChaiML/grpo-q235b-opusd-v1-merged-chai-rm-high-kl-averaged-models in 55.575s
chaiml-grpo-q235b-opusd-55346-v2-uploader: creating bucket guanaco-vllm-models
chaiml-grpo-q235b-opusd-55346-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-opusd-55346-v2-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-grpo-q235b-opusd-55346-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-grpo-q235b-opusd-55346-v2-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-grpo-q235b-opusd-55346-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-opusd-55346-v2-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-grpo-q235b-opusd-55346-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-opusd-55346-v2-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-grpo-q235b-opusd-55346-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-opusd-55346-v2-uploader:   if re.search("-\.", bucket, re.UNICODE):
chaiml-grpo-q235b-opusd-55346-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-grpo-q235b-opusd-55346-v2-uploader:   if re.search("\.\.", bucket, re.UNICODE):
chaiml-grpo-q235b-opusd-55346-v2-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-grpo-q235b-opusd-55346-v2-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-grpo-q235b-opusd-55346-v2-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-grpo-q235b-opusd-55346-v2-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-grpo-q235b-opusd-55346-v2-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-grpo-q235b-opusd-55346-v2-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default
chaiml-grpo-q235b-opusd-55346-v2-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default/chat_template.jinja
chaiml-grpo-q235b-opusd-55346-v2-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default/generation_config.json
chaiml-grpo-q235b-opusd-55346-v2-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default/config.json
chaiml-grpo-q235b-opusd-55346-v2-uploader: cp /dev/shm/model_output/added_tokens.json s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default/added_tokens.json
chaiml-grpo-q235b-opusd-55346-v2-uploader: cp /dev/shm/model_output/quantization_config.json s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default/quantization_config.json
chaiml-grpo-q235b-opusd-55346-v2-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default/special_tokens_map.json
chaiml-grpo-q235b-opusd-55346-v2-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default/merges.txt
chaiml-grpo-q235b-opusd-55346-v2-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default/vocab.json
chaiml-grpo-q235b-opusd-55346-v2-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default/.gitattributes
chaiml-grpo-q235b-opusd-55346-v2-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default/tokenizer_config.json
chaiml-grpo-q235b-opusd-55346-v2-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default/model.safetensors.index.json
chaiml-grpo-q235b-opusd-55346-v2-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default/tokenizer.json
chaiml-grpo-q235b-opusd-55346-v2-uploader: cp /dev/shm/model_output/model-00027-of-00027.safetensors s3://guanaco-vllm-models/chaiml-grpo-q235b-opusd-55346-v2/default/model-00027-of-00027.safetensors
Job chaiml-grpo-q235b-opusd-55346-v2-uploader completed after 145.57s with status: succeeded
Stopping job with name chaiml-grpo-q235b-opusd-55346-v2-uploader
Pipeline stage VLLMUploader completed in 146.79s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-grpo-q235b-opusd-55346-v2
Waiting for inference service chaiml-grpo-q235b-opusd-55346-v2 to be ready
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)
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-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)
HTTP Request: %s %s "%s %d %s"
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_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-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-opusd-55346-v2 ready after 422.57504200935364s
Pipeline stage VLLMDeployer completed in 423.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9009294509887695s
Received healthy response to inference request in 1.6394340991973877s
Received healthy response to inference request in 1.9293105602264404s
Received healthy response to inference request in 1.7673110961914062s
Received healthy response to inference request in 1.3722000122070312s
Received healthy response to inference request in 1.5705657005310059s
Received healthy response to inference request in 1.6134533882141113s
Received healthy response to inference request in 1.5548210144042969s
Received healthy response to inference request in 1.8123083114624023s
Received healthy response to inference request in 1.6002535820007324s
Received healthy response to inference request in 1.620572805404663s
Received healthy response to inference request in 1.5167226791381836s
Received healthy response to inference request in 1.7344391345977783s
Received healthy response to inference request in 1.5906662940979004s
Received healthy response to inference request in 1.3043272495269775s
Received healthy response to inference request in 1.4434642791748047s
Received healthy response to inference request in 1.8213870525360107s
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)
Received healthy response to inference request in 1.3702592849731445s
Received healthy response to inference request in 1.7419095039367676s
Received healthy response to inference request in 1.643310785293579s
Received healthy response to inference request in 1.5556073188781738s
Received healthy response to inference request in 1.5599114894866943s
Received healthy response to inference request in 1.4477097988128662s
Received healthy response to inference request in 1.9056038856506348s
Received healthy response to inference request in 1.658822774887085s
Received healthy response to inference request in 1.5800502300262451s
Received healthy response to inference request in 1.6000149250030518s
Received healthy response to inference request in 1.718501091003418s
Received healthy response to inference request in 1.5060107707977295s
Received healthy response to inference request in 1.6212091445922852s
30 requests
0 failed requests
5th percentile: 1.3711326122283936
10th percentile: 1.4363378524780275
20th percentile: 1.5145802974700928
30th percentile: 1.558620238304138
40th percentile: 1.5864198684692383
50th percentile: 1.6068534851074219
60th percentile: 1.628499126434326
70th percentile: 1.6767262697219847
80th percentile: 1.7469898223876954
90th percentile: 1.8293412923812868
95th percentile: 1.9035003900527954
99th percentile: 1.9224356245994567
mean time: 1.6233695904413858
Pipeline stage StressChecker completed in 53.46s
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 0.60s
Shutdown handler de-registered
chaiml-grpo-q235b-opusd_55346_v2 status is now deployed due to DeploymentManager action
chaiml-grpo-q235b-opusd_55346_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-grpo-q235b-opusd_55346_v2 status is now torndown due to DeploymentManager action