developer_uid: zonemercy
submission_id: chaiml-pony-d3b-mv1-win_84391_v3
model_name: chaiml-pony-d3b-mv1-win_84391_v3
model_group: ChaiML/pony-d3b-mv1-wina
status: torndown
timestamp: 2026-03-31T03:51:05+00:00
num_battles: 10670
num_wins: 5678
celo_rating: 1315.64
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/pony-d3b-mv1-winall-q35b-lr5e6ep2g8
model_architecture: Qwen3_5MoeForConditionalGeneration
model_num_parameters: 33753909248.0
best_of: 16
max_input_tokens: 2048
max_output_tokens: 80
reward_model: default
display_name: chaiml-pony-d3b-mv1-win_84391_v3
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/pony-d3b-mv1-winall-q35b-lr5e6ep2g8
model_size: 34B
ranking_group: single
us_pacific_date: 2026-03-27
win_ratio: 0.5321462043111528
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.8, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>', '####', '<|assistant|>', '</s>', '<|user|>'], 'max_input_tokens': 2048, 'best_of': 16, '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-d3b-mv1-win-84391-v3-uploader
Waiting for job on chaiml-pony-d3b-mv1-win-84391-v3-uploader to finish
chaiml-pony-d3b-mv1-win-84391-v3-uploader: Using quantization_mode: fp8
chaiml-pony-d3b-mv1-win-84391-v3-uploader: Checking if ChaiML/pony-d3b-mv1-winall-q35b-lr5e6ep2g8-FP8 already exists in ChaiML
chaiml-pony-d3b-mv1-win-84391-v3-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-pony-d3b-mv1-win-84391-v3-uploader: Downloading snapshot of ChaiML/pony-d3b-mv1-winall-q35b-lr5e6ep2g8-FP8...
2026-03-28T01:23:30.084060+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v3
chaiml-pony-d3b-mv1-win-84391-v3-uploader: Downloaded in 46.981s
chaiml-pony-d3b-mv1-win-84391-v3-uploader: Processed model ChaiML/pony-d3b-mv1-winall-q35b-lr5e6ep2g8 in 49.462s
chaiml-pony-d3b-mv1-win-84391-v3-uploader: creating bucket guanaco-vllm-models
chaiml-pony-d3b-mv1-win-84391-v3-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-d3b-mv1-win-84391-v3-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-pony-d3b-mv1-win-84391-v3-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-pony-d3b-mv1-win-84391-v3-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-pony-d3b-mv1-win-84391-v3-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-d3b-mv1-win-84391-v3-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-pony-d3b-mv1-win-84391-v3-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-d3b-mv1-win-84391-v3-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-pony-d3b-mv1-win-84391-v3-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-d3b-mv1-win-84391-v3-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-pony-d3b-mv1-win-84391-v3-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-d3b-mv1-win-84391-v3-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-pony-d3b-mv1-win-84391-v3-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-pony-d3b-mv1-win-84391-v3-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-pony-d3b-mv1-win-84391-v3-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-pony-d3b-mv1-win-84391-v3-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-pony-d3b-mv1-win-84391-v3-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-pony-d3b-mv1-win-84391-v3-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v3/default
chaiml-pony-d3b-mv1-win-84391-v3-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v3/default/.gitattributes
chaiml-pony-d3b-mv1-win-84391-v3-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v3/default/generation_config.json
chaiml-pony-d3b-mv1-win-84391-v3-uploader: cp /dev/shm/model_output/recipe.yaml s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v3/default/recipe.yaml
chaiml-pony-d3b-mv1-win-84391-v3-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v3/default/tokenizer_config.json
chaiml-pony-d3b-mv1-win-84391-v3-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v3/default/config.json
chaiml-pony-d3b-mv1-win-84391-v3-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v3/default/chat_template.jinja
chaiml-pony-d3b-mv1-win-84391-v3-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v3/default/tokenizer.json
2026-03-28T01:24:30.179007+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v3
chaiml-pony-d3b-mv1-win-84391-v3-uploader: cp /dev/shm/model_output/model.safetensors s3://guanaco-vllm-models/chaiml-pony-d3b-mv1-win-84391-v3/default/model.safetensors
Job chaiml-pony-d3b-mv1-win-84391-v3-uploader completed after 132.91s with status: succeeded
Stopping job with name chaiml-pony-d3b-mv1-win-84391-v3-uploader
Pipeline stage VLLMUploader completed in 133.71s
run pipeline stage %s
Running pipeline stage VLLMUploaderAMD
Pipeline stage vllm_upload_amd skipped, reason=not amd cluster
Pipeline stage VLLMUploaderAMD completed in 0.10s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 2.98s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-pony-d3b-mv1-win-84391-v3
Waiting for inference service chaiml-pony-d3b-mv1-win-84391-v3 to be ready
2026-03-28T01:25:30.266577+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v3
2026-03-28T01:26:30.363355+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v3
2026-03-28T01:27:30.459068+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v3
Inference service chaiml-pony-d3b-mv1-win-84391-v3 ready after 180.24383401870728s
Pipeline stage VLLMDeployer completed in 180.66s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-28T01:28:30.552329+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v3
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 11.258039712905884s
Received healthy response to inference request in 5.823740243911743s
2026-03-28T01:29:30.656475+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v3
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 16.75234365463257s
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.7392449378967285s
Received healthy response to inference request in 1.3378455638885498s
Received healthy response to inference request in 1.4666924476623535s
2026-03-28T01:30:30.752084+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v3
Received healthy response to inference request in 1.426905632019043s
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.5678775310516357s
Received healthy response to inference request in 1.498342752456665s
Received healthy response to inference request in 1.2653427124023438s
Received healthy response to inference request in 1.4167189598083496s
Received healthy response to inference request in 1.3656151294708252s
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.329693078994751s
Received healthy response to inference request in 1.3680100440979004s
Received healthy response to inference request in 1.4753892421722412s
Received healthy response to inference request in 1.3764781951904297s
2026-03-28T01:31:30.849954+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v3
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.2966039180755615s
Received healthy response to inference request in 1.4023241996765137s
Received healthy response to inference request in 1.3852872848510742s
Received healthy response to inference request in 1.319364309310913s
Received healthy response to inference request in 1.6840052604675293s
30 requests
9 failed requests
5th percentile: 1.3068460941314697
10th percentile: 1.3286602020263671
20th percentile: 1.3675310611724854
30th percentile: 1.3972131252288817
40th percentile: 1.4507777214050293
50th percentile: 1.5331101417541504
60th percentile: 4.573043060302732
70th percentile: 17.762416076660145
80th percentile: 20.128435564041137
90th percentile: 20.191805696487428
95th percentile: 20.372649228572843
99th percentile: 20.547107877731325
mean time: 8.122828618685405
%s, retrying in %s seconds...
Received healthy response to inference request in 1.752047061920166s
Received healthy response to inference request in 1.2438719272613525s
Received healthy response to inference request in 1.2684123516082764s
Received healthy response to inference request in 1.2481920719146729s
Received healthy response to inference request in 1.2990326881408691s
Received healthy response to inference request in 1.2486910820007324s
Received healthy response to inference request in 1.8471732139587402s
Received healthy response to inference request in 1.2354094982147217s
Received healthy response to inference request in 1.318986415863037s
Received healthy response to inference request in 1.2982292175292969s
Received healthy response to inference request in 1.2550342082977295s
Received healthy response to inference request in 1.3105733394622803s
Received healthy response to inference request in 1.318108320236206s
Received healthy response to inference request in 1.2910246849060059s
Received healthy response to inference request in 1.40175461769104s
Received healthy response to inference request in 1.2759981155395508s
Received healthy response to inference request in 1.3173856735229492s
Received healthy response to inference request in 1.3411414623260498s
Received healthy response to inference request in 1.2928414344787598s
Received healthy response to inference request in 1.294508934020996s
Received healthy response to inference request in 1.4799082279205322s
Received healthy response to inference request in 1.5578317642211914s
Received healthy response to inference request in 1.443873643875122s
Received healthy response to inference request in 1.645702838897705s
Received healthy response to inference request in 1.3049376010894775s
2026-03-28T01:32:30.947251+00:00 monitor updated for chaiml-pony-d3b-mv1-win_84391_v3
Received healthy response to inference request in 1.3062422275543213s
Received healthy response to inference request in 1.3998048305511475s
Received healthy response to inference request in 1.570784091949463s
Received healthy response to inference request in 1.3823039531707764s
Received healthy response to inference request in 1.4473209381103516s
30 requests
0 failed requests
5th percentile: 1.2458159923553467
10th percentile: 1.2486411809921265
20th percentile: 1.2744809627532958
30th percentile: 1.2940086841583252
40th percentile: 1.3025756359100342
50th percentile: 1.3139795064926147
60th percentile: 1.3278484344482422
70th percentile: 1.4003897666931153
80th percentile: 1.4538383960723877
90th percentile: 1.5782759666442872
95th percentile: 1.7041921615600584
99th percentile: 1.8195866298675538
mean time: 1.3799042145411173
Pipeline stage StressChecker completed in 290.23s
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 0.90s
Shutdown handler de-registered
chaiml-pony-d3b-mv1-win_84391_v3 status is now deployed due to DeploymentManager action
chaiml-pony-d3b-mv1-win_84391_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-pony-d3b-mv1-win_84391_v3 status is now torndown due to DeploymentManager action