developer_uid: zonemercy
submission_id: chaiml-2fe5-c13f-linear-w01_v17
model_name: test
model_group: ChaiML/2fe5-c13f-linear-
status: torndown
timestamp: 2025-11-15T22:26:30+00:00
num_battles: 6285
num_wins: 3285
celo_rating: 1299.08
family_friendly_score: 0.5304
family_friendly_standard_error: 0.007057986115033097
submission_type: basic
model_repo: ChaiML/2fe5-c13f-linear-w01
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 10
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.9055728181926144, 'latency_mean': 1.1041529452800751, 'latency_p50': 1.0987322330474854, 'latency_p90': 1.2188201904296876}, {'batch_size': 4, 'throughput': 2.0727334690027015, 'latency_mean': 1.9200013041496278, 'latency_p50': 1.9160469770431519, 'latency_p90': 2.118699264526367}, {'batch_size': 5, 'throughput': 2.2688829078050916, 'latency_mean': 2.191290067434311, 'latency_p50': 2.177272319793701, 'latency_p90': 2.4752188205718992}, {'batch_size': 8, 'throughput': 2.617537145778198, 'latency_mean': 3.031715751886368, 'latency_p50': 3.0287282466888428, 'latency_p90': 3.4019526958465574}, {'batch_size': 10, 'throughput': 2.6951595971293183, 'latency_mean': 3.6684124279022217, 'latency_p50': 3.6199612617492676, 'latency_p90': 4.141573858261109}, {'batch_size': 12, 'throughput': 2.768441674821724, 'latency_mean': 4.298648933172226, 'latency_p50': 4.272582530975342, 'latency_p90': 4.889974546432495}, {'batch_size': 15, 'throughput': 2.7834507324878905, 'latency_mean': 5.306525325775146, 'latency_p50': 5.329053997993469, 'latency_p90': 6.107601737976074}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: test
is_internal_developer: True
language_model: ChaiML/2fe5-c13f-linear-w01
model_size: 13B
ranking_group: single
throughput_3p7s: 2.73
us_pacific_date: 2025-11-12
win_ratio: 0.522673031026253
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['User:', 'Bot:', '\n', 'You:', '<|eot_id|>', '####', '</s>', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 10, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", '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 MKMLizer
Starting job with name chaiml-2fe5-c13f-linear-w01-v17-mkmlizer
Waiting for job on chaiml-2fe5-c13f-linear-w01-v17-mkmlizer to finish
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║  belonging to:                                                      ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: Downloaded to shared memory in 27.702s
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: Checking if ChaiML/2fe5-c13f-linear-w01 already exists in ChaiML
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmppp5a38hg, device:0
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-safety-grpo-2025_50335_v5: ('http://chaiml-safety-grpo-2025-50335-v5-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:57114->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: quantized model in 144.178s
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: Processed model ChaiML/2fe5-c13f-linear-w01 in 171.881s
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: creating bucket guanaco-mkml-models
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v17/nvidia
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v17/nvidia/special_tokens_map.json
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v17/nvidia/config.json
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v17/nvidia/tokenizer_config.json
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v17/nvidia/tokenizer.json
chaiml-2fe5-c13f-linear-w01-v17-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v17/nvidia/flywheel_model.0.safetensors
Job chaiml-2fe5-c13f-linear-w01-v17-mkmlizer completed after 237.47s with status: succeeded
Stopping job with name chaiml-2fe5-c13f-linear-w01-v17-mkmlizer
Pipeline stage MKMLizer completed in 238.06s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.76s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-2fe5-c13f-linear-w01-v17
Waiting for inference service chaiml-2fe5-c13f-linear-w01-v17 to be ready
Tearing down inference service chaiml-2fe5-c13f-linear-w01-v17
%s, retrying in %s seconds...
Creating inference service chaiml-2fe5-c13f-linear-w01-v17
Waiting for inference service chaiml-2fe5-c13f-linear-w01-v17 to be ready
Inference service chaiml-2fe5-c13f-linear-w01-v17 ready after 110.96711087226868s
Pipeline stage MKMLDeployer completed in 142.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7692511081695557s
Received healthy response to inference request in 1.1951234340667725s
Received healthy response to inference request in 1.1276543140411377s
Received healthy response to inference request in 1.502234697341919s
Received healthy response to inference request in 2.0499277114868164s
5 requests
0 failed requests
5th percentile: 1.1411481380462647
10th percentile: 1.1546419620513917
20th percentile: 1.1816296100616455
30th percentile: 1.2565456867218017
40th percentile: 1.3793901920318603
50th percentile: 1.502234697341919
60th percentile: 1.6090412616729737
70th percentile: 1.7158478260040282
80th percentile: 1.825386428833008
90th percentile: 1.937657070159912
95th percentile: 1.9937923908233641
99th percentile: 2.038700647354126
mean time: 1.5288382530212403
Pipeline stage StressChecker completed in 10.01s
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
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.62s
Shutdown handler de-registered
chaiml-2fe5-c13f-linear-w01_v17 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2160.64s
Shutdown handler de-registered
chaiml-2fe5-c13f-linear-w01_v17 status is now inactive due to auto deactivation removed underperforming models
chaiml-2fe5-c13f-linear-w01_v17 status is now torndown due to DeploymentManager action