developer_uid: zonemercy
submission_id: chaiml-ir-v4-1-dpo-irv1_19566_v2
model_name: test
model_group: ChaiML/ir-v4-1-dpo_irv13
status: torndown
timestamp: 2025-11-01T20:26:24+00:00
num_battles: 6013
num_wins: 3000
celo_rating: 1293.42
family_friendly_score: 0.4546
family_friendly_standard_error: 0.007041858277471934
submission_type: basic
model_repo: ChaiML/ir-v4-1-dpo_irv13-lr5e6b01-cosine
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.4600456508140817, 'latency_mean': 2.1735775434970854, 'latency_p50': 2.1753358840942383, 'latency_p90': 2.3806750535964967}, {'batch_size': 2, 'throughput': 0.681785063872043, 'latency_mean': 2.928511025905609, 'latency_p50': 2.920910596847534, 'latency_p90': 3.17369704246521}, {'batch_size': 3, 'throughput': 0.8252175524745186, 'latency_mean': 3.623269295692444, 'latency_p50': 3.60890793800354, 'latency_p90': 3.970418047904968}, {'batch_size': 4, 'throughput': 0.9245040940842164, 'latency_mean': 4.306741485595703, 'latency_p50': 4.321538925170898, 'latency_p90': 4.914658689498902}, {'batch_size': 5, 'throughput': 0.9867707431234972, 'latency_mean': 5.04683563709259, 'latency_p50': 5.028684496879578, 'latency_p90': 5.711752223968506}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: test
is_internal_developer: True
language_model: ChaiML/ir-v4-1-dpo_irv13-lr5e6b01-cosine
model_size: 24B
ranking_group: single
throughput_3p7s: 0.84
us_pacific_date: 2025-10-29
win_ratio: 0.49891900881423584
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': ['\n', 'User:', '</s>', 'You:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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-ir-v4-1-dpo-irv1-19566-v2-mkmlizer
Waiting for job on chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer to finish
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ Version: 0.30.2 ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ belonging to: ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ║ ║
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: Downloaded to shared memory in 46.479s
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: Checking if ChaiML/ir-v4-1-dpo_irv13-lr5e6b01-cosine already exists in ChaiML
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpoty7ed3l, device:0
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: quantized model in 284.878s
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: Processed model ChaiML/ir-v4-1-dpo_irv13-lr5e6b01-cosine in 331.358s
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv1-19566-v2/nvidia
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv1-19566-v2/nvidia/config.json
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv1-19566-v2/nvidia/tokenizer_config.json
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv1-19566-v2/nvidia/special_tokens_map.json
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv1-19566-v2/nvidia/tokenizer.json
chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv1-19566-v2/nvidia/flywheel_model.1.safetensors
Job chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer completed after 422.22s with status: succeeded
Stopping job with name chaiml-ir-v4-1-dpo-irv1-19566-v2-mkmlizer
Pipeline stage MKMLizer completed in 422.86s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.25s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ir-v4-1-dpo-irv1-19566-v2
Waiting for inference service chaiml-ir-v4-1-dpo-irv1-19566-v2 to be ready
Inference service chaiml-ir-v4-1-dpo-irv1-19566-v2 ready after 110.75215554237366s
Pipeline stage MKMLDeployer completed in 111.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.316356658935547s
Received healthy response to inference request in 1.7069010734558105s
Received healthy response to inference request in 1.875303030014038s
Received healthy response to inference request in 2.0649960041046143s
Received healthy response to inference request in 1.7841243743896484s
5 requests
0 failed requests
5th percentile: 1.722345733642578
10th percentile: 1.7377903938293457
20th percentile: 1.768679714202881
30th percentile: 1.8023601055145264
40th percentile: 1.8388315677642821
50th percentile: 1.875303030014038
60th percentile: 1.9511802196502686
70th percentile: 2.027057409286499
80th percentile: 2.1152681350708007
90th percentile: 2.215812397003174
95th percentile: 2.2660845279693604
99th percentile: 2.3063022327423095
mean time: 1.9495362281799316
Pipeline stage StressChecker completed in 11.31s
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 0.77s
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 0.66s
Shutdown handler de-registered
chaiml-ir-v4-1-dpo-irv1_19566_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ir-v4-1-dpo-irv1-19566-v2-profiler
Waiting for inference service chaiml-ir-v4-1-dpo-irv1-19566-v2-profiler to be ready
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 3551.57s
Shutdown handler de-registered
chaiml-ir-v4-1-dpo-irv1_19566_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-ir-v4-1-dpo-irv1_19566_v2 status is now torndown due to DeploymentManager action