developer_uid: chai_evaluation_service
submission_id: evelyn777-chai-sft-3b_v7
model_name: evelyn777-chai-sft-3b_v7
model_group: evelyn777/chai-sft-3b
status: inactive
timestamp: 2026-02-07T23:29:01+00:00
num_battles: 11470
num_wins: 3748
celo_rating: 1178.23
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: evelyn777/chai-sft-3b
model_architecture: Qwen2ForCausalLM
model_num_parameters: 3397011456.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
display_name: evelyn777-chai-sft-3b_v7
is_internal_developer: True
language_model: evelyn777/chai-sft-3b
model_size: 3B
ranking_group: single
us_pacific_date: 2026-02-07
win_ratio: 0.3267654751525719
generation_params: {'temperature': 0.85, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.2, 'frequency_penalty': 0.3, 'stopping_words': ['\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {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 evelyn777-chai-sft-3b-v7-uploader
Waiting for job on evelyn777-chai-sft-3b-v7-uploader to finish
evelyn777-chai-sft-3b-v7-uploader: Using quantization_mode: none
evelyn777-chai-sft-3b-v7-uploader: Downloading snapshot of evelyn777/chai-sft-3b...
evelyn777-chai-sft-3b-v7-uploader: Processed model evelyn777/chai-sft-3b in 6.741s
evelyn777-chai-sft-3b-v7-uploader: creating bucket guanaco-vllm-models
evelyn777-chai-sft-3b-v7-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
evelyn777-chai-sft-3b-v7-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
evelyn777-chai-sft-3b-v7-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
evelyn777-chai-sft-3b-v7-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
evelyn777-chai-sft-3b-v7-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
evelyn777-chai-sft-3b-v7-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
evelyn777-chai-sft-3b-v7-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
evelyn777-chai-sft-3b-v7-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
evelyn777-chai-sft-3b-v7-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
evelyn777-chai-sft-3b-v7-uploader:   if re.search("-\.", bucket, re.UNICODE):
evelyn777-chai-sft-3b-v7-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
evelyn777-chai-sft-3b-v7-uploader:   if re.search("\.\.", bucket, re.UNICODE):
evelyn777-chai-sft-3b-v7-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
evelyn777-chai-sft-3b-v7-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
evelyn777-chai-sft-3b-v7-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
evelyn777-chai-sft-3b-v7-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
evelyn777-chai-sft-3b-v7-uploader: Bucket 's3://guanaco-vllm-models/' created
evelyn777-chai-sft-3b-v7-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v7
evelyn777-chai-sft-3b-v7-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v7/.gitattributes
evelyn777-chai-sft-3b-v7-uploader: cp /dev/shm/model_output/added_tokens.json s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v7/added_tokens.json
evelyn777-chai-sft-3b-v7-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v7/config.json
evelyn777-chai-sft-3b-v7-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v7/chat_template.jinja
evelyn777-chai-sft-3b-v7-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v7/generation_config.json
evelyn777-chai-sft-3b-v7-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v7/special_tokens_map.json
evelyn777-chai-sft-3b-v7-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v7/tokenizer_config.json
evelyn777-chai-sft-3b-v7-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v7/model.safetensors.index.json
evelyn777-chai-sft-3b-v7-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v7/merges.txt
evelyn777-chai-sft-3b-v7-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v7/vocab.json
evelyn777-chai-sft-3b-v7-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v7/tokenizer.json
Job evelyn777-chai-sft-3b-v7-uploader completed after 98.57s with status: succeeded
Stopping job with name evelyn777-chai-sft-3b-v7-uploader
Pipeline stage VLLMUploader completed in 102.32s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 3.14s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service evelyn777-chai-sft-3b-v7
Waiting for inference service evelyn777-chai-sft-3b-v7 to be ready
Inference service evelyn777-chai-sft-3b-v7 ready after 160.70379447937012s
Pipeline stage VLLMDeployer completed in 165.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.1614956855773926s
Received healthy response to inference request in 1.178056240081787s
Received healthy response to inference request in 1.1080374717712402s
Received healthy response to inference request in 1.3007521629333496s
Received healthy response to inference request in 1.0531249046325684s
Received healthy response to inference request in 0.8057470321655273s
Received healthy response to inference request in 1.0475313663482666s
Received healthy response to inference request in 0.6970629692077637s
Received healthy response to inference request in 0.6826400756835938s
Received healthy response to inference request in 1.8167717456817627s
Received healthy response to inference request in 0.5092422962188721s
Received healthy response to inference request in 0.6273815631866455s
Received healthy response to inference request in 0.6736240386962891s
Received healthy response to inference request in 0.5177679061889648s
Received healthy response to inference request in 0.8694398403167725s
Received healthy response to inference request in 0.9117124080657959s
Received healthy response to inference request in 0.8011767864227295s
Received healthy response to inference request in 0.9103691577911377s
Received healthy response to inference request in 1.4385135173797607s
Received healthy response to inference request in 1.0099585056304932s
Received healthy response to inference request in 0.6611011028289795s
Received healthy response to inference request in 0.624859094619751s
Received healthy response to inference request in 0.6789555549621582s
Received healthy response to inference request in 0.6601190567016602s
Received healthy response to inference request in 0.8657886981964111s
Received healthy response to inference request in 0.6449813842773438s
Received healthy response to inference request in 0.9177868366241455s
Received healthy response to inference request in 0.8760592937469482s
Received healthy response to inference request in 0.707329273223877s
Received healthy response to inference request in 0.6396231651306152s
30 requests
0 failed requests
5th percentile: 0.5659589409828186
10th percentile: 0.627129316329956
20th percentile: 0.6570915222167969
30th percentile: 0.6773561000823974
40th percentile: 0.7032227516174316
50th percentile: 0.8357678651809692
60th percentile: 0.889783239364624
70th percentile: 0.9454383373260495
80th percentile: 1.064107418060303
90th percentile: 1.1903258323669434
95th percentile: 1.3765209078788754
99th percentile: 1.7070768594741825
mean time: 0.8799003044764201
Pipeline stage StressChecker completed in 36.45s
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 1.45s
Shutdown handler de-registered
evelyn777-chai-sft-3b_v7 status is now deployed due to DeploymentManager action
evelyn777-chai-sft-3b_v7 status is now inactive due to auto deactivation removed underperforming models