developer_uid: chai_backend_admin
submission_id: chaiml-ssnew-v5-dpo-lr5_20359_v3
model_name: chaiml-ssnew-v5-dpo-lr5_20359_v3
model_group: ChaiML/ssnew-v5-dpo-lr5e
status: deployed
timestamp: 2026-02-06T20:32:40+00:00
num_battles: 7635
num_wins: 3752
celo_rating: 9999.0
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/ssnew-v5-dpo-lr5e6b01-lora-W4A16-G128-AutoRound
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
display_name: chaiml-ssnew-v5-dpo-lr5_20359_v3
is_internal_developer: True
language_model: ChaiML/ssnew-v5-dpo-lr5e6b01-lora-W4A16-G128-AutoRound
model_size: 24B
ranking_group: single
us_pacific_date: 2026-02-06
win_ratio: 0.4914210870988867
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', 'You:', '####', '\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s persona: {memory}", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {message}\n', 'response_template': '####\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-ssnew-v5-dpo-lr5-20359-v3-uploader
Waiting for job on chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader to finish
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: Using quantization_mode: none
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: Downloading snapshot of ChaiML/ssnew-v5-dpo-lr5e6b01-lora-W4A16-G128-AutoRound...
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: Fetching 12 files: 0%| | 0/12 [00:00<?, ?it/s] Fetching 12 files: 8%|▊ | 1/12 [00:00<00:02, 3.87it/s] Fetching 12 files: 42%|████▏ | 5/12 [00:08<00:12, 1.76s/it] Fetching 12 files: 100%|██████████| 12/12 [00:08<00:00, 1.44it/s]
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: Downloaded in 8.468s
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: Processed model ChaiML/ssnew-v5-dpo-lr5e6b01-lora-W4A16-G128-AutoRound in 13.845s
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: creating bucket guanaco-vllm-models
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-ssnew-v5-dpo-lr5-20359-v3
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-ssnew-v5-dpo-lr5-20359-v3/.gitattributes
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-ssnew-v5-dpo-lr5-20359-v3/config.json
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/chaiml-ssnew-v5-dpo-lr5-20359-v3/README.md
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-ssnew-v5-dpo-lr5-20359-v3/generation_config.json
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: cp /dev/shm/model_output/recipe.yaml s3://guanaco-vllm-models/chaiml-ssnew-v5-dpo-lr5-20359-v3/recipe.yaml
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-ssnew-v5-dpo-lr5-20359-v3/special_tokens_map.json
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-ssnew-v5-dpo-lr5-20359-v3/model.safetensors.index.json
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-ssnew-v5-dpo-lr5-20359-v3/tokenizer_config.json
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-ssnew-v5-dpo-lr5-20359-v3/tokenizer.json
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: cp /dev/shm/model_output/model-00003-of-00003.safetensors s3://guanaco-vllm-models/chaiml-ssnew-v5-dpo-lr5-20359-v3/model-00003-of-00003.safetensors
HTTP Request: %s %s "%s %d %s"
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: cp /dev/shm/model_output/model-00001-of-00003.safetensors s3://guanaco-vllm-models/chaiml-ssnew-v5-dpo-lr5-20359-v3/model-00001-of-00003.safetensors
chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader: cp /dev/shm/model_output/model-00002-of-00003.safetensors s3://guanaco-vllm-models/chaiml-ssnew-v5-dpo-lr5-20359-v3/model-00002-of-00003.safetensors
Job chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader completed after 258.02s with status: succeeded
Stopping job with name chaiml-ssnew-v5-dpo-lr5-20359-v3-uploader
Pipeline stage VLLMUploader completed in 258.57s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-ssnew-v5-dpo-lr5-20359-v3
Waiting for inference service chaiml-ssnew-v5-dpo-lr5-20359-v3 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
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
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-ssnew-v5-dpo-lr5-20359-v3 ready after 469.2389225959778s
Pipeline stage VLLMDeployer completed in 469.83s
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 1.0759096145629883s
Received healthy response to inference request in 0.9388101100921631s
Received healthy response to inference request in 1.0553710460662842s
Received healthy response to inference request in 1.4042854309082031s
Received healthy response to inference request in 0.9914953708648682s
Received healthy response to inference request in 1.610213041305542s
Received healthy response to inference request in 1.6572999954223633s
Received healthy response to inference request in 1.245553970336914s
Received healthy response to inference request in 2.0214531421661377s
Received healthy response to inference request in 1.373300313949585s
Received healthy response to inference request in 1.4659981727600098s
Received healthy response to inference request in 1.1852526664733887s
Received healthy response to inference request in 1.0992465019226074s
Received healthy response to inference request in 1.4741480350494385s
Received healthy response to inference request in 1.218641757965088s
Received healthy response to inference request in 1.6695542335510254s
Received healthy response to inference request in 1.1973063945770264s
Received healthy response to inference request in 1.2908380031585693s
Received healthy response to inference request in 1.1490910053253174s
Received healthy response to inference request in 1.2866666316986084s
Received healthy response to inference request in 1.4460875988006592s
Received healthy response to inference request in 1.0471525192260742s
Received healthy response to inference request in 1.150116205215454s
Received healthy response to inference request in 1.7840533256530762s
Received healthy response to inference request in 1.5631530284881592s
Received healthy response to inference request in 1.0105969905853271s
Received healthy response to inference request in 1.6086633205413818s
Received healthy response to inference request in 1.3937067985534668s
Received healthy response to inference request in 1.584843635559082s
30 requests
1 failed requests
5th percentile: 1.0000910997390746
10th percentile: 1.0434969663619995
20th percentile: 1.0945791244506835
30th percentile: 1.1747117280960082
40th percentile: 1.2347890853881835
50th percentile: 1.3320691585540771
60th percentile: 1.4210062980651854
70th percentile: 1.5008495330810545
80th percentile: 1.6089732646942139
90th percentile: 1.6810041427612306
95th percentile: 1.9146232247352593
99th percentile: 14.876867992877976
mean time: 1.9708826700846354
%s, retrying in %s seconds...
Received healthy response to inference request in 0.9873933792114258s
Received healthy response to inference request in 0.9221780300140381s
Received healthy response to inference request in 0.9202370643615723s
Received healthy response to inference request in 1.2567131519317627s
Received healthy response to inference request in 1.0794012546539307s
Received healthy response to inference request in 1.3005130290985107s
Received healthy response to inference request in 0.9905350208282471s
Received healthy response to inference request in 0.9953024387359619s
Received healthy response to inference request in 0.9724550247192383s
Received healthy response to inference request in 1.2838308811187744s
Received healthy response to inference request in 1.239199161529541s
Received healthy response to inference request in 1.1128780841827393s
Received healthy response to inference request in 1.3527226448059082s
Received healthy response to inference request in 1.0115952491760254s
Received healthy response to inference request in 0.9818804264068604s
Received healthy response to inference request in 1.1747617721557617s
Received healthy response to inference request in 1.3054847717285156s
Received healthy response to inference request in 1.3627893924713135s
Received healthy response to inference request in 0.9400665760040283s
Received healthy response to inference request in 1.2784223556518555s
Received healthy response to inference request in 1.5507347583770752s
Received healthy response to inference request in 0.9158263206481934s
Received healthy response to inference request in 1.1320209503173828s
Received healthy response to inference request in 1.1337053775787354s
Received healthy response to inference request in 1.4341654777526855s
Received healthy response to inference request in 1.2425618171691895s
Received healthy response to inference request in 1.1298024654388428s
Received healthy response to inference request in 1.2985374927520752s
Received healthy response to inference request in 0.9300012588500977s
Received healthy response to inference request in 1.0220897197723389s
30 requests
0 failed requests
5th percentile: 0.9211104989051819
10th percentile: 0.9292189359664917
20th percentile: 0.9799953460693359
30th percentile: 0.9938722133636475
40th percentile: 1.056476640701294
50th percentile: 1.1309117078781128
60th percentile: 1.2005367279052734
70th percentile: 1.2632259130477905
80th percentile: 1.2989326000213623
90th percentile: 1.3537293195724487
95th percentile: 1.402046239376068
99th percentile: 1.5169296669960024
mean time: 1.1419268449147542
Pipeline stage StressChecker completed in 100.31s
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 0.71s
Shutdown handler de-registered
chaiml-ssnew-v5-dpo-lr5_20359_v3 status is now deployed due to DeploymentManager action