developer_uid: chai_backend_admin
submission_id: chaiml-catholic-teen-ca_34686_v1
model_name: chaiml-catholic-teen-ca_34686_v1
model_group: ChaiML/Catholic-Teen_Cat
status: torndown
timestamp: 2026-03-10T19:33:19+00:00
num_battles: 5810
num_wins: 2609
celo_rating: 9006.39
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/Catholic-Teen_Catholic-Teen_Emma260310184532_sft
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: chaiml-catholic-teen-ca_34686_v1
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: ChaiML/Catholic-Teen_Catholic-Teen_Emma260310184532_sft
model_size: 24B
ranking_group: single
us_pacific_date: 2026-03-10
win_ratio: 0.44905335628227194
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': ['You:', '</s>', '####\n', '####', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{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-catholic-teen-ca-34686-v1-uploader
Waiting for job on chaiml-catholic-teen-ca-34686-v1-uploader to finish
chaiml-catholic-teen-ca-34686-v1-uploader: Using quantization_mode: fp8
chaiml-catholic-teen-ca-34686-v1-uploader: Downloaded in 83.037s
chaiml-catholic-teen-ca-34686-v1-uploader: Loading /tmp/model_input...
chaiml-catholic-teen-ca-34686-v1-uploader: The tokenizer you are loading from '/tmp/model_input' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
chaiml-catholic-teen-ca-34686-v1-uploader: `torch_dtype` is deprecated! Use `dtype` instead!
chaiml-catholic-teen-ca-34686-v1-uploader: Some parameters are on the meta device because they were offloaded to the cpu.
chaiml-catholic-teen-ca-34686-v1-uploader: Applying quantization...
chaiml-catholic-teen-ca-34686-v1-uploader: The tokenizer you are loading from '/tmp/model_input' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
chaiml-catholic-teen-ca-34686-v1-uploader: 2026-03-10T11:55:24.542010-0700 | reset | INFO - Compression lifecycle reset
chaiml-catholic-teen-ca-34686-v1-uploader: 2026-03-10T11:55:24.542919-0700 | from_modifiers | INFO - Creating recipe from modifiers
chaiml-catholic-teen-ca-34686-v1-uploader: 2026-03-10T11:55:24.620578-0700 | initialize | INFO - Compression lifecycle initialized for 1 modifiers
chaiml-catholic-teen-ca-34686-v1-uploader: 2026-03-10T11:55:24.620850-0700 | IndependentPipeline | INFO - Inferred `DataFreePipeline` for `QuantizationModifier`
chaiml-catholic-teen-ca-34686-v1-uploader: Some parameters are on the meta device because they were offloaded to the cpu.
chaiml-catholic-teen-ca-34686-v1-uploader: 2026-03-10T11:55:54.244312-0700 | finalize | INFO - Compression lifecycle finalized for 1 modifiers
chaiml-catholic-teen-ca-34686-v1-uploader: 2026-03-10T11:55:56.360997-0700 | post_process | WARNING - Optimized model is not saved. To save, please provide`output_dir` as input arg.Ex. `oneshot(..., output_dir=...)`
chaiml-catholic-teen-ca-34686-v1-uploader: Saving to /dev/shm/model_output...
chaiml-catholic-teen-ca-34686-v1-uploader: 2026-03-10T11:55:56.388053-0700 | get_model_compressor | INFO - skip_sparsity_compression_stats set to True. Skipping sparsity compression statistic calculations. No sparsity compressor will be applied.
chaiml-catholic-teen-ca-34686-v1-uploader: Cleaning quantization config in /dev/shm/model_output
chaiml-catholic-teen-ca-34686-v1-uploader: Pushing to ChaiML/Catholic-Teen_Catholic-Teen_Emma260310184532_sft-FP8
chaiml-catholic-teen-ca-34686-v1-uploader: Checking if ChaiML/Catholic-Teen_Catholic-Teen_Emma260310184532_sft-FP8 already exists in ChaiML
chaiml-catholic-teen-ca-34686-v1-uploader: Creating repo ChaiML/Catholic-Teen_Catholic-Teen_Emma260310184532_sft-FP8 and uploading /dev/shm/model_output to it
chaiml-catholic-teen-ca-34686-v1-uploader: 







chaiml-catholic-teen-ca-34686-v1-uploader: ---------- 2026-03-10 11:57:44 (0:01:00) ----------
chaiml-catholic-teen-ca-34686-v1-uploader: Files:   hashed 13/13 (24.9G/24.9G) | pre-uploaded: 7/7 (24.9G/24.9G) | committed: 0/13 (0.0/24.9G) | ignored: 0
chaiml-catholic-teen-ca-34686-v1-uploader: Workers: hashing: 0 | get upload mode: 0 | pre-uploading: 0 | committing: 1 | waiting: 125
chaiml-catholic-teen-ca-34686-v1-uploader: ---------------------------------------------------
chaiml-catholic-teen-ca-34686-v1-uploader:                              Processed model ChaiML/Catholic-Teen_Catholic-Teen_Emma260310184532_sft in 247.807s
chaiml-catholic-teen-ca-34686-v1-uploader: creating bucket guanaco-vllm-models
chaiml-catholic-teen-ca-34686-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-catholic-teen-ca-34686-v1-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-catholic-teen-ca-34686-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-catholic-teen-ca-34686-v1-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-catholic-teen-ca-34686-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-catholic-teen-ca-34686-v1-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-catholic-teen-ca-34686-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-catholic-teen-ca-34686-v1-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-catholic-teen-ca-34686-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-catholic-teen-ca-34686-v1-uploader:   if re.search("-\.", bucket, re.UNICODE):
chaiml-catholic-teen-ca-34686-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-catholic-teen-ca-34686-v1-uploader:   if re.search("\.\.", bucket, re.UNICODE):
chaiml-catholic-teen-ca-34686-v1-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-catholic-teen-ca-34686-v1-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-catholic-teen-ca-34686-v1-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-catholic-teen-ca-34686-v1-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-catholic-teen-ca-34686-v1-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-catholic-teen-ca-34686-v1-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-catholic-teen-ca-34686-v1/default
chaiml-catholic-teen-ca-34686-v1-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-catholic-teen-ca-34686-v1/default/special_tokens_map.json
chaiml-catholic-teen-ca-34686-v1-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-catholic-teen-ca-34686-v1/default/model.safetensors.index.json
chaiml-catholic-teen-ca-34686-v1-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-catholic-teen-ca-34686-v1/default/tokenizer_config.json
chaiml-catholic-teen-ca-34686-v1-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-catholic-teen-ca-34686-v1/default/config.json
chaiml-catholic-teen-ca-34686-v1-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-catholic-teen-ca-34686-v1/default/generation_config.json
chaiml-catholic-teen-ca-34686-v1-uploader: cp /dev/shm/model_output/recipe.yaml s3://guanaco-vllm-models/chaiml-catholic-teen-ca-34686-v1/default/recipe.yaml
chaiml-catholic-teen-ca-34686-v1-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-catholic-teen-ca-34686-v1/default/tokenizer.json
chaiml-catholic-teen-ca-34686-v1-uploader: cp /dev/shm/model_output/model-00006-of-00006.safetensors s3://guanaco-vllm-models/chaiml-catholic-teen-ca-34686-v1/default/model-00006-of-00006.safetensors
Job chaiml-catholic-teen-ca-34686-v1-uploader completed after 304.99s with status: succeeded
Stopping job with name chaiml-catholic-teen-ca-34686-v1-uploader
Pipeline stage VLLMUploader completed in 312.35s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 1.31s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-catholic-teen-ca-34686-v1
Waiting for inference service chaiml-catholic-teen-ca-34686-v1 to be ready
Inference service chaiml-catholic-teen-ca-34686-v1 ready after 154.2733108997345s
Pipeline stage VLLMDeployer completed in 158.68s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.7350289821624756s
Received healthy response to inference request in 3.4822838306427s
Received healthy response to inference request in 2.990732192993164s
Received healthy response to inference request in 2.813754081726074s
Received healthy response to inference request in 2.6667301654815674s
Received healthy response to inference request in 3.278139591217041s
Received healthy response to inference request in 2.9015448093414307s
Received healthy response to inference request in 2.713397741317749s
Received healthy response to inference request in 2.8670897483825684s
Received healthy response to inference request in 2.877542734146118s
Received healthy response to inference request in 2.7358436584472656s
Received healthy response to inference request in 2.6671574115753174s
Received healthy response to inference request in 3.339826822280884s
Received healthy response to inference request in 3.1905009746551514s
Received healthy response to inference request in 2.9280474185943604s
Received healthy response to inference request in 3.2408010959625244s
Received healthy response to inference request in 2.9982573986053467s
Received healthy response to inference request in 2.918929100036621s
Received healthy response to inference request in 2.703213930130005s
Received healthy response to inference request in 3.030156373977661s
Received healthy response to inference request in 2.758394241333008s
Received healthy response to inference request in 3.1276862621307373s
Received healthy response to inference request in 3.008807897567749s
Received healthy response to inference request in 3.3217647075653076s
Received healthy response to inference request in 3.2503862380981445s
Received healthy response to inference request in 2.644948959350586s
Received healthy response to inference request in 3.379525899887085s
Received healthy response to inference request in 3.2969675064086914s
Received healthy response to inference request in 3.1540963649749756s
30 requests
1 failed requests
5th percentile: 2.666922426223755
10th percentile: 2.6996082782745363
20th percentile: 2.7356807231903075
30th percentile: 2.85108904838562
40th percentile: 2.911975383758545
50th percentile: 2.9944947957992554
60th percentile: 3.0691683292388916
70th percentile: 3.205591011047363
80th percentile: 3.281905174255371
90th percentile: 3.343796730041504
95th percentile: 3.436042761802673
99th percentile: 16.51411107540132
mean time: 3.62861754099528
%s, retrying in %s seconds...
Received healthy response to inference request in 2.6942660808563232s
Received healthy response to inference request in 2.663442611694336s
Received healthy response to inference request in 2.955024480819702s
Received healthy response to inference request in 2.686591863632202s
Received healthy response to inference request in 3.0517680644989014s
Received healthy response to inference request in 2.917987585067749s
Received healthy response to inference request in 2.6809263229370117s
Received healthy response to inference request in 2.808361768722534s
Received healthy response to inference request in 2.885943651199341s
Received healthy response to inference request in 3.1533427238464355s
Received healthy response to inference request in 3.1391305923461914s
Received healthy response to inference request in 2.787104606628418s
Received healthy response to inference request in 2.853522777557373s
Received healthy response to inference request in 2.8507378101348877s
Received healthy response to inference request in 3.0606300830841064s
Received healthy response to inference request in 2.786985158920288s
Received healthy response to inference request in 2.9304628372192383s
Received healthy response to inference request in 3.423290252685547s
Received healthy response to inference request in 2.6987390518188477s
Received healthy response to inference request in 2.688119888305664s
Received healthy response to inference request in 3.0533607006073s
Received healthy response to inference request in 3.0829780101776123s
Received healthy response to inference request in 2.912972927093506s
Received healthy response to inference request in 3.33897066116333s
Received healthy response to inference request in 3.2639551162719727s
Received healthy response to inference request in 3.697124719619751s
Received healthy response to inference request in 3.170135974884033s
Received healthy response to inference request in 2.6742584705352783s
Received healthy response to inference request in 2.727797031402588s
Received healthy response to inference request in 3.0395703315734863s
30 requests
0 failed requests
5th percentile: 2.6772590041160584
10th percentile: 2.686025309562683
20th percentile: 2.697844457626343
30th percentile: 2.787068772315979
40th percentile: 2.852408790588379
50th percentile: 2.9154802560806274
60th percentile: 2.988842821121216
70th percentile: 3.055541515350342
80th percentile: 3.1419730186462402
90th percentile: 3.2714566707611086
95th percentile: 3.3853464365005492
99th percentile: 3.617712724208832
mean time: 2.955916738510132
Pipeline stage StressChecker completed in 324.75s
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 6.25s
Shutdown handler de-registered
chaiml-catholic-teen-ca_34686_v1 status is now deployed due to DeploymentManager action
chaiml-catholic-teen-ca_34686_v1 status is now torndown due to DeploymentManager action