chaiml-reward-dpo-7c16-_56312

developer_uid: rirv938
submission_id: chaiml-reward-dpo-7c16-_56312_v1
model_name: chaiml-reward-dpo-7c16-_56312_v1
model_group: ChaiML/reward-dpo-7c16-c
status: torndown
timestamp: 2026-02-22T10:31:44+00:00
num_battles: 10721
num_wins: 6288
celo_rating: 1359.0
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/reward-dpo-7c16-chaiml-235b-sft-new-rm-_42002_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-7c16-_56312_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/reward-dpo-7c16-chaiml-235b-sft-new-rm-_42002_v1-W4A16
model_size: 19B
ranking_group: single
us_pacific_date: 2026-02-19
win_ratio: 0.5865124521966234
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': ['You:', '###', '</s>', '<|im_end|>', '<|im_start|>'], '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-7c16-56312-v1-uploader
Waiting for job on chaiml-reward-dpo-7c16-56312-v1-uploader to finish
chaiml-reward-dpo-7c16-56312-v1-uploader: Using quantization_mode: w4a16
chaiml-reward-dpo-7c16-56312-v1-uploader: Repo ChaiML/reward-dpo-7c16-chaiml-235b-sft-new-rm-_42002_v1-W4A16 already ends in W4A16. Skipping...
chaiml-reward-dpo-7c16-56312-v1-uploader: Checking if ChaiML/reward-dpo-7c16-chaiml-235b-sft-new-rm-_42002_v1-W4A16 already exists in ChaiML
chaiml-reward-dpo-7c16-56312-v1-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-reward-dpo-7c16-56312-v1-uploader: Downloading snapshot of ChaiML/reward-dpo-7c16-chaiml-235b-sft-new-rm-_42002_v1-W4A16...
HTTP Request: %s %s "%s %d %s"
chaiml-reward-dpo-7c16-56312-v1-uploader: Downloaded in 67.705s
chaiml-reward-dpo-7c16-56312-v1-uploader: Processed model ChaiML/reward-dpo-7c16-chaiml-235b-sft-new-rm-_42002_v1-W4A16 in 68.247s
chaiml-reward-dpo-7c16-56312-v1-uploader: creating bucket guanaco-vllm-models
chaiml-reward-dpo-7c16-56312-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-reward-dpo-7c16-56312-v1-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-reward-dpo-7c16-56312-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-reward-dpo-7c16-56312-v1-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-reward-dpo-7c16-56312-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-reward-dpo-7c16-56312-v1-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-reward-dpo-7c16-56312-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-reward-dpo-7c16-56312-v1-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-reward-dpo-7c16-56312-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-reward-dpo-7c16-56312-v1-uploader:   if re.search("-\.", bucket, re.UNICODE):
chaiml-reward-dpo-7c16-56312-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-reward-dpo-7c16-56312-v1-uploader:   if re.search("\.\.", bucket, re.UNICODE):
chaiml-reward-dpo-7c16-56312-v1-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-reward-dpo-7c16-56312-v1-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-reward-dpo-7c16-56312-v1-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-reward-dpo-7c16-56312-v1-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-reward-dpo-7c16-56312-v1-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-reward-dpo-7c16-56312-v1-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/.gitattributes
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/added_tokens.json s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/added_tokens.json
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/chat_template.jinja
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/generation_config.json
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/special_tokens_map.json
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/tokenizer_config.json
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/config.json
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/quantization_config.json s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/quantization_config.json
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/merges.txt
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/vocab.json
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/tokenizer.json
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model.safetensors.index.json
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', '')
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00027-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00027-of-00027.safetensors
HTTP Request: %s %s "%s %d %s"
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', '')
HTTP Request: %s %s "%s %d %s"
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-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00011-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00011-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00012-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00012-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00014-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00014-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00008-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00008-of-00027.safetensors
HTTP Request: %s %s "%s %d %s"
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00001-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00001-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00022-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00022-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00021-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00021-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00017-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00017-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00024-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00024-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', '')
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00010-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00010-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00026-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00026-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00004-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00004-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00018-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00018-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00009-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00009-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00015-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00015-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00025-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00025-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00020-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00020-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00002-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00002-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00003-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00003-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00016-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00016-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00023-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00023-of-00027.safetensors
chaiml-reward-dpo-7c16-56312-v1-uploader: cp /dev/shm/model_output/model-00019-of-00027.safetensors s3://guanaco-vllm-models/chaiml-reward-dpo-7c16-56312-v1/default/model-00019-of-00027.safetensors
Job chaiml-reward-dpo-7c16-56312-v1-uploader completed after 1002.65s with status: succeeded
Stopping job with name chaiml-reward-dpo-7c16-56312-v1-uploader
Pipeline stage VLLMUploader completed in 1003.58s
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-7c16-56312-v1
Waiting for inference service chaiml-reward-dpo-7c16-56312-v1 to be ready
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"
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', '')
HTTP Request: %s %s "%s %d %s"
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', '')
HTTP Request: %s %s "%s %d %s"
Inference service chaiml-reward-dpo-7c16-56312-v1 ready after 1023.969033241272s
Pipeline stage VLLMDeployer completed in 1024.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0803964138031006s
Received healthy response to inference request in 1.8987150192260742s
Received healthy response to inference request in 2.07427716255188s
Received healthy response to inference request in 1.9214541912078857s
Received healthy response to inference request in 1.9010708332061768s
Received healthy response to inference request in 2.248076915740967s
Received healthy response to inference request in 1.8785700798034668s
Received healthy response to inference request in 1.908033847808838s
Received healthy response to inference request in 1.917081594467163s
Received healthy response to inference request in 2.1278648376464844s
Received healthy response to inference request in 1.9558138847351074s
Received healthy response to inference request in 1.9474165439605713s
Received healthy response to inference request in 1.9406161308288574s
Received healthy response to inference request in 2.0017335414886475s
Received healthy response to inference request in 2.046099901199341s
Received healthy response to inference request in 1.9381287097930908s
Received healthy response to inference request in 1.9510667324066162s
Received healthy response to inference request in 2.112190008163452s
Received healthy response to inference request in 2.016869306564331s
Received healthy response to inference request in 1.8916997909545898s
Received healthy response to inference request in 1.920898199081421s
Received healthy response to inference request in 2.0491466522216797s
Received healthy response to inference request in 1.919445276260376s
Received healthy response to inference request in 2.077582836151123s
Received healthy response to inference request in 1.9626343250274658s
Received healthy response to inference request in 1.987391471862793s
Received healthy response to inference request in 2.1426331996917725s
Received healthy response to inference request in 2.0881600379943848s
Received healthy response to inference request in 2.104097604751587s
Received healthy response to inference request in 1.9899179935455322s
30 requests
0 failed requests
5th percentile: 1.8948566436767578
10th percentile: 1.9008352518081666
20th percentile: 1.9189725399017334
30th percentile: 1.9331263542175292
40th percentile: 1.9496066570281982
50th percentile: 1.9750128984451294
60th percentile: 2.007787847518921
70th percentile: 2.0566858053207397
80th percentile: 2.0819491386413573
90th percentile: 2.1137574911117554
95th percentile: 2.135987436771393
99th percentile: 2.2174982380867005
mean time: 1.9999694347381591
Pipeline stage StressChecker completed in 63.94s
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 0.69s
Shutdown handler de-registered
chaiml-reward-dpo-7c16-_56312_v1 status is now deployed due to DeploymentManager action
chaiml-reward-dpo-7c16-_56312_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-reward-dpo-7c16-_56312_v1 status is now torndown due to DeploymentManager action