chaiml-4d70-fd43-linear-w01

developer_uid: chai_backend_admin

submission_id: chaiml-4d70-fd43-linear-w01_v31

model_name: chaiml-4d70-fd43-linear-w01_v31

model_group: ChaiML/4d70-fd43-linear-

status: torndown

timestamp: 2026-02-10T18:51:42+00:00

num_battles: 10729

num_wins: 5457

celo_rating: 1314.44

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/4d70-fd43-linear-w01

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1800

max_output_tokens: 74

reward_model: default

display_name: chaiml-4d70-fd43-linear-w01_v31

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/4d70-fd43-linear-w01

model_size: 13B

ranking_group: single

us_pacific_date: 2026-02-07

win_ratio: 0.5086214931494082

generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.08, 'frequency_penalty': 0.08, 'stopping_words': ['\n', '###', '<|im_start|>', '</s>', '<|im_end|>'], 'max_input_tokens': 1800, 'best_of': 8, 'max_output_tokens': 74}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {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-4d70-fd43-linear-w01-v31-uploader
Waiting for job on chaiml-4d70-fd43-linear-w01-v31-uploader to finish
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
chaiml-4d70-fd43-linear-w01-v31-uploader: Using quantization_mode: none
chaiml-4d70-fd43-linear-w01-v31-uploader: Downloading snapshot of ChaiML/4d70-fd43-linear-w01...
chaiml-4d70-fd43-linear-w01-v31-uploader: 
Fetching 14 files:   0%|          | 0/14 [00:00<?, ?it/s]
Fetching 14 files:   7%|▋         | 1/14 [00:00<00:03,  3.41it/s]
Fetching 14 files:  43%|████▎     | 6/14 [00:07<00:10,  1.37s/it]
Fetching 14 files:  50%|█████     | 7/14 [00:10<00:11,  1.61s/it]
Fetching 14 files:  64%|██████▍   | 9/14 [00:10<00:05,  1.06s/it]
Fetching 14 files: 100%|██████████| 14/14 [00:10<00:00,  1.31it/s]
chaiml-4d70-fd43-linear-w01-v31-uploader: Downloaded in 10.790s
chaiml-4d70-fd43-linear-w01-v31-uploader: Processed model ChaiML/4d70-fd43-linear-w01 in 19.805s
chaiml-4d70-fd43-linear-w01-v31-uploader: creating bucket guanaco-vllm-models
chaiml-4d70-fd43-linear-w01-v31-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-4d70-fd43-linear-w01-v31-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-4d70-fd43-linear-w01-v31-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-4d70-fd43-linear-w01-v31-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-4d70-fd43-linear-w01-v31-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-4d70-fd43-linear-w01-v31-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-4d70-fd43-linear-w01-v31-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-4d70-fd43-linear-w01-v31-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-4d70-fd43-linear-w01-v31-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-4d70-fd43-linear-w01-v31-uploader:   if re.search("-\.", bucket, re.UNICODE):
chaiml-4d70-fd43-linear-w01-v31-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-4d70-fd43-linear-w01-v31-uploader:   if re.search("\.\.", bucket, re.UNICODE):
chaiml-4d70-fd43-linear-w01-v31-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-4d70-fd43-linear-w01-v31-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-4d70-fd43-linear-w01-v31-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-4d70-fd43-linear-w01-v31-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-4d70-fd43-linear-w01-v31-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-4d70-fd43-linear-w01-v31-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-4d70-fd43-linear-w01-v31
chaiml-4d70-fd43-linear-w01-v31-uploader: cp /dev/shm/model_output/model-00001-of-00005.safetensors s3://guanaco-vllm-models/chaiml-4d70-fd43-linear-w01-v31/model-00001-of-00005.safetensors
chaiml-4d70-fd43-linear-w01-v31-uploader: cp /dev/shm/model_output/model-00005-of-00005.safetensors s3://guanaco-vllm-models/chaiml-4d70-fd43-linear-w01-v31/model-00005-of-00005.safetensors
chaiml-4d70-fd43-linear-w01-v31-uploader: cp /dev/shm/model_output/model-00003-of-00005.safetensors s3://guanaco-vllm-models/chaiml-4d70-fd43-linear-w01-v31/model-00003-of-00005.safetensors
chaiml-4d70-fd43-linear-w01-v31-uploader: cp /dev/shm/model_output/model-00002-of-00005.safetensors s3://guanaco-vllm-models/chaiml-4d70-fd43-linear-w01-v31/model-00002-of-00005.safetensors
chaiml-4d70-fd43-linear-w01-v31-uploader: cp /dev/shm/model_output/model-00004-of-00005.safetensors s3://guanaco-vllm-models/chaiml-4d70-fd43-linear-w01-v31/model-00004-of-00005.safetensors
Job chaiml-4d70-fd43-linear-w01-v31-uploader completed after 138.75s with status: succeeded
Stopping job with name chaiml-4d70-fd43-linear-w01-v31-uploader
Pipeline stage VLLMUploader completed in 145.94s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 4.39s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-4d70-fd43-linear-w01-v31
Waiting for inference service chaiml-4d70-fd43-linear-w01-v31 to be ready
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
HTTP Request: %s %s "%s %d %s"
Inference service chaiml-4d70-fd43-linear-w01-v31 ready after 733.5630548000336s
Pipeline stage VLLMDeployer completed in 742.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8924682140350342s
Received healthy response to inference request in 1.854140043258667s
Received healthy response to inference request in 1.6062633991241455s
Received healthy response to inference request in 1.7571337223052979s
Received healthy response to inference request in 1.4458811283111572s
Received healthy response to inference request in 1.8388781547546387s
Received healthy response to inference request in 1.4862425327301025s
Received healthy response to inference request in 1.8079578876495361s
Received healthy response to inference request in 2.1203227043151855s
Received healthy response to inference request in 2.0458199977874756s
Received healthy response to inference request in 1.8660941123962402s
Received healthy response to inference request in 1.9499807357788086s
Received healthy response to inference request in 1.8258295059204102s
Received healthy response to inference request in 2.5571045875549316s
Received healthy response to inference request in 1.9320464134216309s
Received healthy response to inference request in 1.9607539176940918s
Received healthy response to inference request in 1.9252533912658691s
Received healthy response to inference request in 1.949082374572754s
Received healthy response to inference request in 1.9082658290863037s
Received healthy response to inference request in 1.7774176597595215s
Received healthy response to inference request in 1.8012430667877197s
Received healthy response to inference request in 1.7717247009277344s
Received healthy response to inference request in 1.6064331531524658s
Received healthy response to inference request in 1.7116193771362305s
Received healthy response to inference request in 1.8395919799804688s
Received healthy response to inference request in 1.9517185688018799s
read tcp 127.0.0.1:35174->127.0.0.1:8080: read: connection reset by peer
Received unhealthy response to inference request!
Received healthy response to inference request in 3.0905022621154785s
Received healthy response to inference request in 2.105034112930298s
Received healthy response to inference request in 2.1535377502441406s
30 requests
1 failed requests
5th percentile: 1.5402519226074218
10th percentile: 1.6064161777496337
20th percentile: 1.7688065052032471
30th percentile: 1.8059434413909912
40th percentile: 1.8393064498901368
50th percentile: 1.8792811632156372
60th percentile: 1.9279706001281738
70th percentile: 1.95050208568573
80th percentile: 2.05766282081604
90th percentile: 2.1938944339752204
95th percentile: 2.7856025338172903
99th percentile: 3.0562976717948915
mean time: 1.9503632227579752
%s, retrying in %s seconds...
Received healthy response to inference request in 2.1088552474975586s
Received healthy response to inference request in 2.0973761081695557s
Received healthy response to inference request in 1.6632933616638184s
Received healthy response to inference request in 1.8797876834869385s
Received healthy response to inference request in 1.5012714862823486s
Received healthy response to inference request in 1.6493289470672607s
Received healthy response to inference request in 1.4760115146636963s
Received healthy response to inference request in 1.6789741516113281s
Received healthy response to inference request in 1.57145094871521s
Received healthy response to inference request in 1.475287914276123s
Received healthy response to inference request in 2.1411616802215576s
Received healthy response to inference request in 1.819124460220337s
Received healthy response to inference request in 1.4971859455108643s
Received healthy response to inference request in 1.5826847553253174s
Received healthy response to inference request in 1.5951685905456543s
Received healthy response to inference request in 1.7319862842559814s
Received healthy response to inference request in 1.806980848312378s
Received healthy response to inference request in 1.548335313796997s
Received healthy response to inference request in 1.7506725788116455s
Received healthy response to inference request in 1.5038650035858154s
Received healthy response to inference request in 1.641373872756958s
Received healthy response to inference request in 1.4953248500823975s
Received healthy response to inference request in 1.624774694442749s
Received healthy response to inference request in 1.717942476272583s
Received healthy response to inference request in 1.5612006187438965s
Received healthy response to inference request in 1.6109347343444824s
Received healthy response to inference request in 1.660576581954956s
Received healthy response to inference request in 1.9724020957946777s
Received healthy response to inference request in 1.6253046989440918s
Received healthy response to inference request in 1.8333377838134766s
30 requests
0 failed requests
5th percentile: 1.4847025156021119
10th percentile: 1.4969998359680177
20th percentile: 1.5394412517547609
30th percentile: 1.579314613342285
40th percentile: 1.6192387104034425
50th percentile: 1.6453514099121094
60th percentile: 1.6695656776428223
70th percentile: 1.7375921726226806
80th percentile: 1.8219671249389648
90th percentile: 1.9848994970321656
95th percentile: 2.103689634799957
99th percentile: 2.131792814731598
mean time: 1.694065841039022
Pipeline stage StressChecker completed in 143.13s
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-4d70-fd43-linear-w01_v31 status is now deployed due to DeploymentManager action
chaiml-4d70-fd43-linear-w01_v31 status is now inactive due to auto deactivation removed underperforming models
chaiml-4d70-fd43-linear-w01_v31 status is now torndown due to DeploymentManager action