chaiml-reward-dpo-52f9-_47866

developer_uid: rirv938
submission_id: chaiml-reward-dpo-52f9-_47866_v2
model_name: chaiml-reward-dpo-52f9-_47866_v2
model_group: ChaiML/reward-dpo-52f9-c
status: torndown
timestamp: 2026-02-22T01:01:57+00:00
num_battles: 10527
num_wins: 5957
celo_rating: 1347.4
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/reward-dpo-52f9-chaiml-235b-sft-prod-rm_38783_v1-W4A16
model_architecture: Qwen3MoeForCausalLM
model_num_parameters: 18790207488.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 80
reward_model: default
display_name: chaiml-reward-dpo-52f9-_47866_v2
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/reward-dpo-52f9-chaiml-235b-sft-prod-rm_38783_v1-W4A16
model_size: 19B
ranking_group: single
us_pacific_date: 2026-02-18
win_ratio: 0.5658782179158355
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>', '###', '<|im_start|>', 'You:', '</s>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 80}
formatter: {'memory_template': '<|im_start|>system\nRespond as a high quality storyteller.<|im_end|>\n<|im_start|>user\n', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '<|im_end|>\n<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
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-reward-dpo-52f9-47866-v2-uploader
Waiting for job on chaiml-reward-dpo-52f9-47866-v2-uploader to finish
chaiml-reward-dpo-52f9-47866-v2-uploader: Using quantization_mode: w4a16
chaiml-reward-dpo-52f9-47866-v2-uploader: Repo ChaiML/reward-dpo-52f9-chaiml-235b-sft-prod-rm_38783_v1-W4A16 already ends in W4A16. Skipping...
chaiml-reward-dpo-52f9-47866-v2-uploader: Checking if ChaiML/reward-dpo-52f9-chaiml-235b-sft-prod-rm_38783_v1-W4A16 already exists in ChaiML
chaiml-reward-dpo-52f9-47866-v2-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-reward-dpo-52f9-47866-v2-uploader: Downloading snapshot of ChaiML/reward-dpo-52f9-chaiml-235b-sft-prod-rm_38783_v1-W4A16...
chaiml-reward-dpo-52f9-47866-v2-uploader: Downloaded in 54.092s
chaiml-reward-dpo-52f9-47866-v2-uploader: Processed model ChaiML/reward-dpo-52f9-chaiml-235b-sft-prod-rm_38783_v1-W4A16 in 54.724s
chaiml-reward-dpo-52f9-47866-v2-uploader: creating bucket guanaco-vllm-models
chaiml-reward-dpo-52f9-47866-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-reward-dpo-52f9-47866-v2-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-reward-dpo-52f9-47866-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-reward-dpo-52f9-47866-v2-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-reward-dpo-52f9-47866-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-reward-dpo-52f9-47866-v2-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-reward-dpo-52f9-47866-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-reward-dpo-52f9-47866-v2-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-reward-dpo-52f9-47866-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-reward-dpo-52f9-47866-v2-uploader:   if re.search("-\.", bucket, re.UNICODE):
chaiml-reward-dpo-52f9-47866-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-reward-dpo-52f9-47866-v2-uploader:   if re.search("\.\.", bucket, re.UNICODE):
chaiml-reward-dpo-52f9-47866-v2-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-reward-dpo-52f9-47866-v2-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-reward-dpo-52f9-47866-v2-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-reward-dpo-52f9-47866-v2-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-reward-dpo-52f9-47866-v2-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-reward-dpo-52f9-47866-v2-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/.gitattributes
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/chat_template.jinja
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/generation_config.json
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/added_tokens.json s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/added_tokens.json
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/tokenizer_config.json
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/special_tokens_map.json
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/quantization_config.json s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/quantization_config.json
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/config.json
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/merges.txt
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/vocab.json
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/tokenizer.json
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model.safetensors.index.json
Failed to get response for submission chaiml-mistral-24b-2048_54327_v6: ('http://chaiml-mistral-24b-2048-54327-v6-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00027-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00027-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00003-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00003-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00023-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00023-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00002-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00002-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00005-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00005-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00014-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00014-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00021-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00021-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00015-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00015-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00016-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00016-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00026-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00026-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00024-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00024-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00013-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00013-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00019-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00019-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00012-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00012-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00011-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00011-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00001-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00001-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00018-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00018-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00025-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00025-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00007-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00007-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00008-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00008-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00009-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00009-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00020-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00020-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00017-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00017-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00010-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00010-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00004-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00004-of-00027.safetensors
chaiml-reward-dpo-52f9-47866-v2-uploader: cp /dev/shm/model_output/model-00022-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-52f9-47866-v2/default/model-00022-of-00027.safetensors
Failed to get response for submission chaiml-mistral-24b-2048-_2678_v3: ('http://chaiml-mistral-24b-2048-2678-v3-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-mistral-24b-2048-_2678_v3: ('http://chaiml-mistral-24b-2048-2678-v3-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Job chaiml-reward-dpo-52f9-47866-v2-uploader completed after 419.97s with status: succeeded
Stopping job with name chaiml-reward-dpo-52f9-47866-v2-uploader
Pipeline stage VLLMUploader completed in 420.66s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-reward-dpo-52f9-47866-v2
Waiting for inference service chaiml-reward-dpo-52f9-47866-v2 to be ready
Failed to get response for submission chaiml-grpo-q235b-kimid_37540_v1: HTTPConnectionPool(host='chaiml-grpo-q235b-kimid-37540-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-mistral-24b-2048-_2678_v3: ('http://chaiml-mistral-24b-2048-2678-v3-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-grpo-q235b-kimid_37540_v1: HTTPConnectionPool(host='chaiml-grpo-q235b-kimid-37540-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-mistral-24b-2048_15988_v1: ('http://chaiml-mistral-24b-2048-15988-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-mistral-24b-2048_15988_v1: ('http://chaiml-mistral-24b-2048-15988-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
HTTP Request: %s %s "%s %d %s"
Inference service chaiml-reward-dpo-52f9-47866-v2 ready after 663.7946646213531s
Pipeline stage VLLMDeployer completed in 664.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9973325729370117s
Received healthy response to inference request in 1.9537913799285889s
Received healthy response to inference request in 1.9704985618591309s
Received healthy response to inference request in 1.9186971187591553s
Received healthy response to inference request in 2.17880916595459s
Received healthy response to inference request in 2.0834481716156006s
Received healthy response to inference request in 1.953134298324585s
Received healthy response to inference request in 2.137911558151245s
Received healthy response to inference request in 2.098649501800537s
Received healthy response to inference request in 2.0075929164886475s
Received healthy response to inference request in 2.3270504474639893s
Received healthy response to inference request in 2.2325077056884766s
Received healthy response to inference request in 2.0673751831054688s
Received healthy response to inference request in 2.0843069553375244s
Received healthy response to inference request in 2.191009521484375s
Received healthy response to inference request in 2.0067410469055176s
Received healthy response to inference request in 2.1173384189605713s
Received healthy response to inference request in 2.18554949760437s
Received healthy response to inference request in 2.0204100608825684s
Received healthy response to inference request in 1.9227263927459717s
Received healthy response to inference request in 2.126660108566284s
Received healthy response to inference request in 2.0570967197418213s
Received healthy response to inference request in 1.955186128616333s
Received healthy response to inference request in 1.9532148838043213s
Received healthy response to inference request in 2.034323215484619s
Received healthy response to inference request in 1.9159255027770996s
Received healthy response to inference request in 1.992671012878418s
Received healthy response to inference request in 2.899641752243042s
Received healthy response to inference request in 2.0137155055999756s
Received healthy response to inference request in 2.1191298961639404s
30 requests
0 failed requests
5th percentile: 1.9205102920532227
10th percentile: 1.9500935077667236
20th percentile: 1.9549071788787842
30th percentile: 1.9959341049194337
40th percentile: 2.0112664699554443
50th percentile: 2.04570996761322
60th percentile: 2.0837916851043703
70th percentile: 2.117875862121582
80th percentile: 2.146091079711914
90th percentile: 2.195159339904785
95th percentile: 2.2845062136650083
99th percentile: 2.7335902738571174
mean time: 2.084081506729126
Pipeline stage StressChecker completed in 68.51s
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 0.66s
Shutdown handler de-registered
chaiml-reward-dpo-52f9-_47866_v2 status is now deployed due to DeploymentManager action
chaiml-reward-dpo-52f9-_47866_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-reward-dpo-52f9-_47866_v2 status is now torndown due to DeploymentManager action