chaiml-pony-v1-q235b-lr_32150

developer_uid: zonemercy
submission_id: chaiml-pony-v1-q235b-lr_32150_v4
model_name: chaiml-pony-v1-q235b-lr_32150_v4
model_group: ChaiML/pony-v1-q235b-lr1
status: torndown
timestamp: 2026-03-02T09:51:02+00:00
num_battles: 11067
num_wins: 6006
celo_rating: 1322.97
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/pony-v1-q235b-lr1e4ep1r64g8
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-pony-v1-q235b-lr_32150_v4
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/pony-v1-q235b-lr1e4ep1r64g8
model_size: 19B
ranking_group: single
us_pacific_date: 2026-02-27
win_ratio: 0.5426944971537002
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|>', '<|user|>', '<|im_end|>', '</s>', '####', '</think>'], '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-pony-v1-q235b-lr-32150-v4-uploader
Waiting for job on chaiml-pony-v1-q235b-lr-32150-v4-uploader to finish
chaiml-pony-v1-q235b-lr-32150-v4-uploader: Using quantization_mode: w4a16
chaiml-pony-v1-q235b-lr-32150-v4-uploader: Checking if ChaiML/pony-v1-q235b-lr1e4ep1r64g8-W4A16 already exists in ChaiML
chaiml-pony-v1-q235b-lr-32150-v4-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-pony-v1-q235b-lr-32150-v4-uploader: Downloading snapshot of ChaiML/pony-v1-q235b-lr1e4ep1r64g8-W4A16...
chaiml-pony-v1-q235b-lr-32150-v4-uploader: Downloaded in 48.773s
chaiml-pony-v1-q235b-lr-32150-v4-uploader: Processed model ChaiML/pony-v1-q235b-lr1e4ep1r64g8 in 49.370s
chaiml-pony-v1-q235b-lr-32150-v4-uploader: creating bucket guanaco-vllm-models
chaiml-pony-v1-q235b-lr-32150-v4-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v1-q235b-lr-32150-v4-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-pony-v1-q235b-lr-32150-v4-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-pony-v1-q235b-lr-32150-v4-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-pony-v1-q235b-lr-32150-v4-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v1-q235b-lr-32150-v4-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-pony-v1-q235b-lr-32150-v4-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v1-q235b-lr-32150-v4-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-pony-v1-q235b-lr-32150-v4-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v1-q235b-lr-32150-v4-uploader:   if re.search("-\.", bucket, re.UNICODE):
chaiml-pony-v1-q235b-lr-32150-v4-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v1-q235b-lr-32150-v4-uploader:   if re.search("\.\.", bucket, re.UNICODE):
chaiml-pony-v1-q235b-lr-32150-v4-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-pony-v1-q235b-lr-32150-v4-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-pony-v1-q235b-lr-32150-v4-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-pony-v1-q235b-lr-32150-v4-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-pony-v1-q235b-lr-32150-v4-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-pony-v1-q235b-lr-32150-v4-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/.gitattributes
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/quantization_config.json s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/quantization_config.json
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/merges.txt
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/chat_template.jinja
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/tokenizer_config.json
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/config.json
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/added_tokens.json s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/added_tokens.json
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/generation_config.json
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/special_tokens_map.json
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/vocab.json
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model.safetensors.index.json
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/tokenizer.json
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00027-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00027-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00011-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00011-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00001-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00001-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00020-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00020-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00021-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00021-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00007-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00007-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00017-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00017-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00023-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00023-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00009-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00009-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00019-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00019-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00026-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00026-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00003-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00003-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00022-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00022-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00006-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00006-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00024-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00024-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00004-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00004-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00025-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00025-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00016-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00016-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00014-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00014-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00015-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00015-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00002-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00002-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00012-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00012-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00008-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00008-of-00027.safetensors
chaiml-pony-v1-q235b-lr-32150-v4-uploader: cp /dev/shm/model_output/model-00005-of-00027.safetensors s3://guanaco-vllm-models/chaiml-pony-v1-q235b-lr-32150-v4/default/model-00005-of-00027.safetensors
Job chaiml-pony-v1-q235b-lr-32150-v4-uploader completed after 206.98s with status: succeeded
Stopping job with name chaiml-pony-v1-q235b-lr-32150-v4-uploader
Pipeline stage VLLMUploader completed in 207.34s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.30s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-pony-v1-q235b-lr-32150-v4
Waiting for inference service chaiml-pony-v1-q235b-lr-32150-v4 to be ready
Inference service chaiml-pony-v1-q235b-lr-32150-v4 ready after 600.4066495895386s
Pipeline stage VLLMDeployer completed in 600.75s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3286750316619873s
Received healthy response to inference request in 2.2596137523651123s
Received healthy response to inference request in 1.9565508365631104s
Received healthy response to inference request in 1.8397860527038574s
Received healthy response to inference request in 2.0306856632232666s
Received healthy response to inference request in 2.180842638015747s
Received healthy response to inference request in 1.9167194366455078s
Received healthy response to inference request in 2.061580181121826s
Received healthy response to inference request in 2.0688648223876953s
Received healthy response to inference request in 1.9071426391601562s
Received healthy response to inference request in 1.9297795295715332s
Received healthy response to inference request in 1.9429645538330078s
Received healthy response to inference request in 1.9461636543273926s
Received healthy response to inference request in 2.0269482135772705s
Received healthy response to inference request in 1.9559946060180664s
Received healthy response to inference request in 2.0140037536621094s
Received healthy response to inference request in 2.0986077785491943s
Received healthy response to inference request in 1.97172212600708s
Received healthy response to inference request in 1.9928820133209229s
Received healthy response to inference request in 2.081908941268921s
Received healthy response to inference request in 1.9117259979248047s
Received healthy response to inference request in 2.203773260116577s
Received healthy response to inference request in 1.8964202404022217s
Received healthy response to inference request in 1.9614593982696533s
Received healthy response to inference request in 1.8443388938903809s
Received healthy response to inference request in 1.9679059982299805s
Received healthy response to inference request in 1.9974853992462158s
Received healthy response to inference request in 1.9274256229400635s
Received healthy response to inference request in 1.8860361576080322s
Received healthy response to inference request in 1.966010570526123s
30 requests
0 failed requests
5th percentile: 1.863102662563324
10th percentile: 1.8953818321228026
20th percentile: 1.9157207489013672
30th percentile: 1.9390090465545655
40th percentile: 1.9563283443450927
50th percentile: 1.9669582843780518
60th percentile: 1.99472336769104
70th percentile: 2.0280694484710695
80th percentile: 2.0714736461639403
90th percentile: 2.1831357002258303
95th percentile: 2.2344855308532714
99th percentile: 2.3086472606658934
mean time: 2.0024672587712606
Pipeline stage StressChecker completed in 64.57s
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 0.68s
Shutdown handler de-registered
chaiml-pony-v1-q235b-lr_32150_v4 status is now deployed due to DeploymentManager action
chaiml-pony-v1-q235b-lr_32150_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-pony-v1-q235b-lr_32150_v4 status is now torndown due to DeploymentManager action