developer_uid: zonemercy
submission_id: chaiml-grpo-nis-12bsft_56492_v18
model_name: chaiml-grpo-nis-12bsft_56492_v18
model_group: ChaiML/grpo_nis_12bsftju
status: torndown
timestamp: 2025-10-07T11:20:33+00:00
num_battles: 5522
num_wins: 2733
celo_rating: 1280.68
family_friendly_score: 0.513
family_friendly_standard_error: 0.007068677386894949
submission_type: basic
model_repo: ChaiML/grpo_nis_12bsftjun_v4_cp_beta30_rm1_s1_step1370_e10_merged
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1280
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.8807400584783711, 'latency_mean': 1.135284423828125, 'latency_p50': 1.1338180303573608, 'latency_p90': 1.2548359870910644}, {'batch_size': 4, 'throughput': 2.037989892200748, 'latency_mean': 1.955627235174179, 'latency_p50': 1.9633287191390991, 'latency_p90': 2.20807044506073}, {'batch_size': 5, 'throughput': 2.23352689749213, 'latency_mean': 2.2239421439170837, 'latency_p50': 2.2209115028381348, 'latency_p90': 2.473351550102234}, {'batch_size': 8, 'throughput': 2.5954127467780785, 'latency_mean': 3.0677725577354433, 'latency_p50': 3.0855698585510254, 'latency_p90': 3.498900270462036}, {'batch_size': 10, 'throughput': 2.6991943765479585, 'latency_mean': 3.672716828584671, 'latency_p50': 3.662283778190613, 'latency_p90': 4.223639869689942}, {'batch_size': 12, 'throughput': 2.805198010972512, 'latency_mean': 4.236265170574188, 'latency_p50': 4.26616358757019, 'latency_p90': 4.967799687385559}, {'batch_size': 15, 'throughput': 2.852857487433407, 'latency_mean': 5.191760112047195, 'latency_p50': 5.218498706817627, 'latency_p90': 5.922353482246399}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-grpo-nis-12bsft_56492_v18
is_internal_developer: True
language_model: ChaiML/grpo_nis_12bsftjun_v4_cp_beta30_rm1_s1_step1370_e10_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 2.73
us_pacific_date: 2025-10-07
win_ratio: 0.4949293734154292
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.15, 'frequency_penalty': 0.15, 'stopping_words': ['</s>', '###', 'You:', '\n'], 'max_input_tokens': 1280, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', '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-grpo-nis-12bsft-56492-v18-mkmlizer
Waiting for job on chaiml-grpo-nis-12bsft-56492-v18-mkmlizer to finish
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║                                                                     ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║                                                                     ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║                                                                     ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║  belonging to:                                                      ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║                                                                     ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ║                                                                     ║
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: Downloaded to shared memory in 25.478s
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: Checking if ChaiML/grpo_nis_12bsftjun_v4_cp_beta30_rm1_s1_step1370_e10_merged already exists in ChaiML
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp0aub06r5, device:0
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: quantized model in 145.496s
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: Processed model ChaiML/grpo_nis_12bsftjun_v4_cp_beta30_rm1_s1_step1370_e10_merged in 170.975s
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: creating bucket guanaco-mkml-models
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-grpo-nis-12bsft-56492-v18/nvidia
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-grpo-nis-12bsft-56492-v18/nvidia/config.json
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-grpo-nis-12bsft-56492-v18/nvidia/special_tokens_map.json
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-grpo-nis-12bsft-56492-v18/nvidia/tokenizer_config.json
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-grpo-nis-12bsft-56492-v18/nvidia/tokenizer.json
chaiml-grpo-nis-12bsft-56492-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-grpo-nis-12bsft-56492-v18/nvidia/flywheel_model.0.safetensors
Job chaiml-grpo-nis-12bsft-56492-v18-mkmlizer completed after 248.16s with status: succeeded
Stopping job with name chaiml-grpo-nis-12bsft-56492-v18-mkmlizer
Pipeline stage MKMLizer completed in 248.66s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-grpo-nis-12bsft-56492-v18
Waiting for inference service chaiml-grpo-nis-12bsft-56492-v18 to be ready
Inference service chaiml-grpo-nis-12bsft-56492-v18 ready after 61.1468243598938s
Pipeline stage MKMLDeployer completed in 61.66s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5698978900909424s
Received healthy response to inference request in 1.2702608108520508s
Received healthy response to inference request in 1.2560620307922363s
Received healthy response to inference request in 1.209282636642456s
Received healthy response to inference request in 1.0695075988769531s
5 requests
0 failed requests
5th percentile: 1.0974626064300537
10th percentile: 1.1254176139831542
20th percentile: 1.1813276290893555
30th percentile: 1.2186385154724122
40th percentile: 1.2373502731323243
50th percentile: 1.2560620307922363
60th percentile: 1.261741542816162
70th percentile: 1.267421054840088
80th percentile: 1.330188226699829
90th percentile: 1.4500430583953858
95th percentile: 1.509970474243164
99th percentile: 1.5579124069213868
mean time: 1.2750021934509277
Pipeline stage StressChecker completed in 7.54s
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 0.59s
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 0.58s
Shutdown handler de-registered
chaiml-grpo-nis-12bsft_56492_v18 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 2046.81s
Shutdown handler de-registered
chaiml-grpo-nis-12bsft_56492_v18 status is now inactive due to auto deactivation removed underperforming models
chaiml-grpo-nis-12bsft_56492_v18 status is now torndown due to DeploymentManager action